def setupModel(params, settings, dt, simTime, populationsInput,
populationsNoiseSource, populationsRN, populationsPN,
populationsAN, projectionsPNAN):
maxDelay = max([
params['MAX_DELAY_RATECODE_TO_CLUSTER_RN'],
params['MAX_DELAY_CLASS_ACTIVITY_TO_CLUSTER_AN']
])
spynnaker.setup(timestep=dt, min_delay=1, max_delay=maxDelay)
setupLayerInput(params, settings, populationsInput)
setupLayerNoiseSource(params, simTime, populationsNoiseSource)
setupLayerRN(params, neuronModel, cell_params, populationsInput[0],
populationsNoiseSource[0], populationsRN)
setupLayerPN(params, neuronModel, cell_params, populationsRN,
populationsPN)
setupLayerAN(params, settings, neuronModel, cell_params,
populationsInput[1], populationsNoiseSource[0], populationsPN,
populationsAN, projectionsPNAN)
printModelConfigurationSummary(params, populationsInput,
populationsNoiseSource, populationsRN,
populationsPN, populationsAN)
def mapping_process():
###################################
SIM_TIME = TIME_SLOT*DATA_AMOUNT ##
###################################
twitter_text_vectors = sentence_to_vec()
orig = get_nearest_neighbor(twitter_text_vectors)
show_result(orig,1,'./retrived_data/original_classification')
response_space = generate_vr_response(twitter_text_vectors)
spiking_space = generate_spiking_time(response_space)
np.savetxt("./retrived_data/input_time.txt",spiking_space,fmt='%s',delimiter=',',newline='\n')
spynnaker.setup(timestep=1)
spynnaker.set_number_of_neurons_per_core(spynnaker.IF_curr_exp, 250)
pn_population = setupLayer_PN(spiking_space)
kc_population = setupLayer_KC()
kc_population.record(["spikes"])
pn_kc_projection = setupProjection_PN_KC(pn_population,kc_population)
spynnaker.run(SIM_TIME)
neo = kc_population.get_data(variables=["spikes"])
spikeData_original= neo.segments[0].spiketrains
spynnaker.end()
return spikeData_original
def setupModel(settings,params, dt,simTime,populationsInput, populationsNoiseSource, populationsRN,populationsPN,populationsAN,projectionsPNAN):
maxDelay = max([params['MAX_DELAY_RATECODE_TO_CLUSTER_RN'],params['MAX_DELAY_CLASS_ACTIVITY_TO_CLUSTER_AN']])
spynnaker.setup(timestep=dt,min_delay=1,max_delay=maxDelay)
rnSpikeInjectionPort = settings['RN_SPIKE_INJECTION_PORT']
rnSpikeInjectionPopLabel = settings['RN_SPIKE_INJECTION_POP_LABEL']
classActivationSpikeInjectionPort = settings['CLASS_ACTIVATION_SPIKE_INJECTION_PORT']
classActivationSpikeInjectionPopLabel = settings['CLASS_ACTIVATION_SPIKE_INJECTION_POP_LABEL']
learning = settings['LEARNING']
print 'Setting up input layer..'
numInjectionPops = setupLayerInput(params,rnSpikeInjectionPort,rnSpikeInjectionPopLabel, classActivationSpikeInjectionPort,classActivationSpikeInjectionPopLabel, populationsInput,learning)
print numInjectionPops , ' spikeInjection populations were needed to accomodate ', params['NUM_VR'], " VRs"
print 'Setting up noise source layer..'
setupLayerNoiseSource(params, simTime, populationsNoiseSource)
print 'Setting up RN layer..'
numInputPops = len(populationsInput)
injectionPops = populationsInput[1:len(populationsInput)]
numInjectionPops = len(injectionPops)
setupLayerRN(params,neuronModel, cell_params, injectionPops, populationsNoiseSource[0], populationsRN)
#setupLayerRN(params,neuronModel, cell_params, injectionPops, populationsRN)
print 'Setting up PN layer..'
setupLayerPN(params, neuronModel, cell_params, populationsRN, populationsPN)
print 'Setting up AN layer..'
setupLayerAN(params, settings, neuronModel, cell_params, populationsInput[0], populationsNoiseSource[0], populationsPN, populationsAN,learning,projectionsPNAN)
printModelConfigurationSummary(params, populationsInput, populationsNoiseSource, populationsRN, populationsPN, populationsAN)
def live_spike_receive_translated(self):
self.stored_data = list()
db_conn = DatabaseConnection(local_port=None)
db_conn.add_database_callback(self.database_callback)
p.setup(1.0)
p.set_number_of_neurons_per_core(p.SpikeSourceArray, 5)
pop = p.Population(
25, p.SpikeSourceArray([[1000 + (i * 10)] for i in range(25)]))
p.external_devices.activate_live_output_for(
pop,
translate_keys=True,
database_notify_port_num=db_conn.local_port,
tag=1,
use_prefix=True,
key_prefix=self.PREFIX,
prefix_type=EIEIOPrefix.UPPER_HALF_WORD)
p.run(1500)
p.end()
self.listener.close()
self.conn.close()
self.assertGreater(len(self.stored_data), 0)
for key, time in self.stored_data:
self.assertEqual(key >> 16, self.PREFIX)
self.assertEqual(1000 + ((key & 0xFFFF) * 10), time)
def test(spikeTimes, trained_weights,label):
#spikeTimes = extractSpikes(sample)
runTime = int(max(max(spikeTimes)))+100
##########################################
sim.setup(timestep=1)
pre_pop = sim.Population(input_size, sim.SpikeSourceArray, {'spike_times': spikeTimes}, label="pre_pop")
post_pop = sim.Population(output_size, sim.IF_curr_exp , cell_params_lif, label="post_pop")
if len(trained_weights) > input_size:
weigths = [[0 for j in range(output_size)] for i in range(input_size)] #np array? size 1024x25
k=0
for i in range(input_size):
for j in range(output_size):
weigths[i][j] = trained_weights[k]
k += 1
else:
weigths = trained_weights
connections = []
#k = 0
for n_pre in range(input_size): # len(untrained_weights) = input_size
for n_post in range(output_size): # len(untrained_weight[0]) = output_size; 0 or any n_pre
#connections.append((n_pre, n_post, weigths[n_pre][n_post]*(wMax), __delay__))
connections.append((n_pre, n_post, weigths[n_pre][n_post]*(wMax)/max(trained_weights), __delay__)) #
#k += 1
prepost_proj = sim.Projection(pre_pop, post_pop, sim.FromListConnector(connections), synapse_type=sim.StaticSynapse(), receptor_type='excitatory') # no more learning !!
#inhib_proj = sim.Projection(post_pop, post_pop, sim.AllToAllConnector(), synapse_type=sim.StaticSynapse(weight=inhibWeight, delay=__delay__), receptor_type='inhibitory')
# no more lateral inhib
post_pop.record(['v', 'spikes'])
sim.run(runTime)
neo = post_pop.get_data(['v', 'spikes'])
spikes = neo.segments[0].spiketrains
v = neo.segments[0].filter(name='v')[0]
f1=pplt.Figure(
# plot voltage
pplt.Panel(v, ylabel="Membrane potential (mV)", xticks=True, yticks=True, xlim=(0, runTime+100)),
# raster plot
pplt.Panel(spikes, xlabel="Time (ms)", xticks=True, yticks=True, markersize=2, xlim=(0, runTime+100)),
title='Test with label ' + str(label),
annotations='Test with label ' + str(label)
)
f1.save('plot/'+str(trylabel)+str(label)+'_test.png')
f1.fig.texts=[]
print("Weights:{}".format(prepost_proj.get('weight', 'list')))
weight_list = [prepost_proj.get('weight', 'list'), prepost_proj.get('weight', format='list', with_address=False)]
#predict_label=
sim.end()
return spikes
def __init__( self, time, num_neurons ):
threading.Thread.__init__( self )
p.setup( timestep=1.0, min_delay=1.0, max_delay=144.0 )
self.time = time
self.num_neurons = num_neurons
self.loop_connections = list()
self.weight_to_spike = 2.0
self.delay = 17
self.cell_params = {
'cm' : 0.25,
'i_offset' : 0.0,
'tau_m' : 20.0,
'tau_refrac': 2.0,
'tau_syn_E' : 5.0,
'tau_syn_I' : 5.0,
'v_reset' : -70.0,
'v_rest' : -65.0,
'v_thresh' : -50.0
}
self.injector_cell_params = {
'host_port_number' : 12345,
'host_ip_address' : "localhost",
'virtual_key' : 458752,
'prefix' : 7,
'prefix_type' : q.EIEIOPrefixType.UPPER_HALF_WORD
}
for i in range( 0, self.num_neurons - 1 ):
single_connection = ( i, ( ( i + 1 ) % self.num_neurons ), self.weight_to_spike, self.delay )
self.loop_connections.append( single_connection )
self.injection_connections = {
'pop1' : [( 0, 0, self.weight_to_spike, 1 )],
'pop2' : [( 1, 0, self.weight_to_spike, 1 )]
}
self.populations = {
# pop name num neurons neuron type cell parameters label
"injector" : p.Population( 2, q.ReverseIpTagMultiCastSource, self.injector_cell_params, label='spike_injector' ),
"pop1" : p.Population( self.num_neurons, p.IF_curr_exp, self.cell_params, label='pop1' ),
"pop2" : p.Population( self.num_neurons, p.IF_curr_exp, self.cell_params, label='pop2' ),
"pop3" : p.Population( self.num_neurons, p.IF_curr_exp, self.cell_params, label='pop3' )
}
self.projections = [
p.Projection( self.populations['pop1'], self.populations['pop1'], p.FromListConnector( self.loop_connections ) ),
p.Projection( self.populations['pop2'], self.populations['pop2'], p.FromListConnector( self.loop_connections ) ),
p.Projection( self.populations['pop2'], self.populations['pop3'], p.FromListConnector( self.loop_connections ) ),
p.Projection( self.populations['injector'], self.populations['pop1'], p.FromListConnector( self.injection_connections['pop1'] ) ),
p.Projection( self.populations['injector'], self.populations['pop2'], p.FromListConnector( self.injection_connections['pop2'] ) )
]
def generate_data():
spikesTrain = []
organisedData = {}
for i in range(input_class):
for j in range(input_len):
neuid = (i, j)
organisedData[neuid] = []
for i in range(input_len):
for j in range(output_size):
neuid = (j, i)
organisedData[neuid].append(j * input_len * v_co * 5 + i * v_co)
organisedData[neuid].append(j * input_len * v_co * 5 +
input_len * v_co * 1 + i * v_co)
organisedData[neuid].append(j * input_len * v_co * 5 +
input_len * v_co * 2 + i * v_co)
organisedData[neuid].append(j * input_len * v_co * 5 +
input_len * v_co * 3 + i * v_co)
organisedData[neuid].append(j * input_len * v_co * 5 +
input_len * v_co * 4 + i * v_co)
organisedData[neuid].append(input_len * v_co * (3 * 5 + j) +
i * v_co)
#organisedData[neuid].append(i*v_co+2)
# if neuid not in organisedData:
# organisedData[neuid]=[i*v_co]
# else:
# organisedData[neuid].append(i*v_co)
for i in range(input_class):
for j in range(input_len):
neuid = (i, j)
organisedData[neuid].sort()
spikesTrain.append(organisedData[neuid])
runTime = int(max(max(spikesTrain)))
sim.setup(timestep=1)
noise = sim.Population(input_size, sim.SpikeSourcePoisson(), label='noise')
noise.record(['spikes']) #noise
sim.run(runTime)
neonoise = noise.get_data(["spikes"])
spikesnoise = neonoise.segments[0].spiketrains #noise
sim.end()
for i in range(input_size):
for noisespike in spikesnoise[i]:
spikesTrain[i].append(noisespike)
spikesTrain[i].sort()
return spikesTrain
def setupModel(settings,params, dt,simTime,populationsInput, populationsNoiseSource, populationsRN,populationsPN,populationsAN,projectionsPNAN):
maxDelay = max([params['MAX_DELAY_RATECODE_TO_CLUSTER_RN'],params['MAX_DELAY_CLASS_ACTIVITY_TO_CLUSTER_AN']])
spynnaker.setup(timestep=dt,min_delay=1,max_delay=maxDelay)
spikeSourceVrResponsePath = settings['SPIKE_SOURCE_VR_RESPONSE_PATH']
spikeSourceActiveClassPath = settings['SPIKE_SOURCE_ACTIVE_CLASS_PATH']
learning = settings['LEARNING']
setupLayerInput(params, spikeSourceVrResponsePath, spikeSourceActiveClassPath, populationsInput,learning)
setupLayerNoiseSource(params, simTime, populationsNoiseSource)
setupLayerRN(params,neuronModel, cell_params, populationsInput[0], populationsNoiseSource[0], populationsRN)
setupLayerPN(params, neuronModel, cell_params, populationsRN, populationsPN)
setupLayerAN(params, settings, neuronModel, cell_params, populationsInput[1], populationsNoiseSource[0], populationsPN, populationsAN,learning,projectionsPNAN)
printModelConfigurationSummary(params, populationsInput, populationsNoiseSource, populationsRN, populationsPN, populationsAN)
def mapping_process():
assert SIM_TIME > 0
spynnaker.setup(timestep=1)
spynnaker.set_number_of_neurons_per_core(spynnaker.IF_curr_exp, 50)
time_space = readData()
pn_population = setupLayer_PN(time_space)
kc_population = setupLayer_KC()
kc_population.record(["spikes"])
pn_kc_projection = setupProjection_PN_KC(pn_population, kc_population)
spynnaker.run(SIM_TIME)
neo = kc_population.get_data(variables=["spikes"])
spikeData_original = neo.segments[0].spiketrains
spynnaker.end()
return spikeData_original
def main():
# setup timestep of simulation and minimum and maximum synaptic delays
setup(timestep=simulationTimestep, min_delay=minSynapseDelay, max_delay=maxSynapseDelay, threads=4)
# create a spike sources
retinaLeft = createSpikeSource("Retina Left")
retinaRight = createSpikeSource("Retina Right")
# create network and attach the spike sources
network = createCooperativeNetwork(retinaLeft=retinaLeft, retinaRight=retinaRight)
# run simulation for time in milliseconds
print "Simulation started..."
run(simulationTime)
print "Simulation ended."
# plot results
plotExperiment(retinaLeft, retinaRight, network)
# finalise program and simulation
end()
def setupModel(
params,
settings,
dt,
simTime,
populationsInput,
populationsNoiseSource,
populationsRN,
populationsPN,
populationsAN,
projectionsPNAN,
):
maxDelay = max([params["MAX_DELAY_RATECODE_TO_CLUSTER_RN"], params["MAX_DELAY_CLASS_ACTIVITY_TO_CLUSTER_AN"]])
spynnaker.setup(timestep=dt, min_delay=1, max_delay=maxDelay)
setupLayerInput(params, settings, populationsInput)
setupLayerNoiseSource(params, simTime, populationsNoiseSource)
setupLayerRN(params, neuronModel, cell_params, populationsInput[0], populationsNoiseSource[0], populationsRN)
setupLayerPN(params, neuronModel, cell_params, populationsRN, populationsPN)
setupLayerAN(
params,
settings,
neuronModel,
cell_params,
populationsInput[1],
populationsNoiseSource[0],
populationsPN,
populationsAN,
projectionsPNAN,
)
printModelConfigurationSummary(
params, populationsInput, populationsNoiseSource, populationsRN, populationsPN, populationsAN
)
def mapping_process():
###################################
SIM_TIME = TIME_SLOT * DATA_AMOUNT ##
###################################
spynnaker.setup(timestep=1)
spynnaker.set_number_of_neurons_per_core(spynnaker.IF_curr_exp, 50)
# time_space = readData()
# Manage to obtain data correctly
pn_population = setupLayer_PN(time_space)
kc_population = setupLayer_KC()
kc_population.record(["spikes"])
pn_kc_projection = setupProjection_PN_KC(pn_population, kc_population)
spynnaker.run(SIM_TIME)
neo = kc_population.get_data(variables=["spikes"])
spikeData_original = neo.segments[0].spiketrains
spynnaker.end()
return spikeData_original
def mapping_process():
###################################
SIM_TIME = TIME_SLOT*DATA_AMOUNT ##
###################################
response_space = generate_vr_response()
spiking_space = generate_spiking_time(response_space)
spynnaker.setup(timestep=1)
spynnaker.set_number_of_neurons_per_core(spynnaker.IF_curr_exp, 250)
pn_population = setupLayer_PN(spiking_space)
kc_population = setupLayer_KC()
kc_population.record(["spikes"])
pn_kc_projection = setupProjection_PN_KC(pn_population,kc_population)
spynnaker.run(SIM_TIME)
neo = kc_population.get_data(variables=["spikes"])
spikeData_original= neo.segments[0].spiketrains
spynnaker.end()
return spikeData_original
import json
from spinn_machine.json_utils import (to_json, from_json_path)
import pyNN.spiNNaker as sim
n_boards = 480
n_chips_required = 0 - n_boards
sim.setup(timestep=1.0, n_chips_required=n_chips_required)
machine = sim.get_machine()
sim.end()
print("Got machine")
jpath = "{}board.json".format(n_boards)
j_machine = to_json(machine)
with open(jpath, "w") as f:
json.dump(j_machine, f)
machine2 = from_json_path(jpath)
j_machine2 = to_json(machine2)
testpath = "test.json"
with open(testpath, "w") as f:
json.dump(j_machine2, f)
assert j_machine == j_machine2
import pyNN.spiNNaker as sim
sim.setup()
p1 = sim.Population(3, sim.SpikeSourceArray, {"spike_times": [1.0, 2.0, 3.0]})
p2 = sim.Population(3, sim.SpikeSourceArray, {"spike_times": [[10.0], [20.0], [30.0]]})
p3 = sim.Population(4, sim.IF_cond_exp, {})
sim.Projection(p2, p3, sim.FromListConnector([
(0, 0, 0.1, 1.0), (1, 1, 0.1, 1.0), (2, 2, 0.1, 1.0)]))
#sim.Projection(p1, p3, sim.FromListConnector([(0, 3, 0.1, 1.0)])) # works if this line is added
sim.run(100.0)
return spike_times_1, spike_times_2 #millisecond*second*minutes*hour in a day #runtime = 1000*60*60*24 runtime = 1000#*60*10 #10 min stimtime = 500 weight_to_spike = 8. timestep = 1. min_delay = 1. max_delay = 20. sim.setup(timestep=timestep, min_delay = min_delay, max_delay = max_delay) max_weight = 10. min_weight = 0.0 a_plus = 0.1 a_minus = 0.12 tau_plus = 20. tau_minus = 20. num_exc = 800 num_inh = 200 total_neurons = num_exc + num_inh max_conn_per_neuron = 100 conn_prob = 0.1#float(max_conn_per_neuron)/float(total_neurons) cell_type = sim.IZK_curr_exp
# Population parameters
model = sim.IF_cond_exp
cell_params = {'cm': 0.25, # nF
'i_offset': 0.0,
'tau_m': 10.0,
'tau_refrac': 2.0,
'tau_syn_E': 2.5,
'tau_syn_I': 2.5,
'v_reset': -70.0,
'v_rest': -65.0,
'v_thresh': -55.4
}
# SpiNNaker setup
sim.setup(timestep=0.1, min_delay=0.1, max_delay=1.0)
# -------------------------------------------------------------------
# Experiment loop
# -------------------------------------------------------------------
projections = []
sim_time = 0
for t in delta_t:
# Calculate phase of input spike trains
# If M.A.D., take into account dendritic delay
if mad:
# Pre after post
if t > 0:
post_phase = 0
pre_phase = t + 1
# Post after pre
LOGDEBUG = 1
LOGINFO = 2
LOGLEVEL = LOGINFO
#### DEFAULTS
tau_syn = 100 # default value
neurons_per_core = 100 # default value
#### COUNTERS
n_outs = 0 # output counter for placing NEF_out populations in chip 0,0
# Setting up the connection with the DB and the number of cells
spinn.setup(db_name = os.path.abspath('%s/nengo_model.sqlite' % pacman.BINARIES_DIRECTORY))
spinn.get_db().set_number_of_neurons_per_core('NEF_out_2d', neurons_per_core*2) # this will set one population per core
#spinn.get_db().set_number_of_neurons_per_core('IF_curr_exp_32', neurons_per_core) # this will set one population per core
spinn.get_db().set_number_of_neurons_per_core('IF_NEF_input_2d', neurons_per_core*2) # this will set one population per core
# PACMAN INTERFACES
class general_cell():
"""
PACMAN Interface class giving a cell type with parameters, class, size, label, id and mapping constraints
"""
def __init__(self, cellname):
self.__name__ = cellname
class MySpiNNakerLinkDevice(ApplicationSpiNNakerLinkVertex):
def __init__(
self, n_neurons, spinnaker_link_id, label=None):
ApplicationSpiNNakerLinkVertex.__init__(
self, n_neurons, spinnaker_link_id, label=label)
class MySpiNNakerLinkDeviceDataHolder(DataHolder):
def __init__(self, spinnaker_link_id, label=None):
DataHolder.__init__(
self, {"spinnaker_link_id": spinnaker_link_id, "label": label})
@staticmethod
def build_model():
return MySpiNNakerLinkDevice
p.setup(1.0)
poisson = p.Population(1, p.SpikeSourcePoisson(rate=100))
device = p.Population(1, MySpiNNakerLinkDeviceDataHolder(spinnaker_link_id=1))
p.external_devices.activate_live_output_to(poisson, device)
p.run(100)
p.end()
setattr(population, variable, s[label][variable])
if label != 'InputLayer':
population.set(i_offset=s[label]['i_offset'])
layers.append(population)
return layers, s['labels'], n_neurons
# run for every participant and every fold
accs_all = []
stds_all = []
for part in participants:
print("running particpant: " + str(part))
allfoldacc = []
for fold in np.arange(0, 5):
pynn.setup(dt, min_delay=dt)
if spin:
pynn.set_number_of_neurons_per_core(pynn.IF_curr_exp, 64)
path = "models/subject_" + str(part) + "/fold" + str(fold)
# load data
test_data = np.load(path + "/x_test.npz")['arr_0']
test_labels = np.load(path + "/y_test.npz")['arr_0']
pred_labels = []
num_test = len(test_data)
# create network
network, labels, n_neurons = load_assembly(
path, "tsfold" + str(fold) + "_nest", pynn)
# Get the number of cores and use this to make the simulation
n_cores = 0
for chip in machine.chips:
for processor in chip.processors:
if not processor.is_monitor:
n_cores += 1
n_pops = int(math.floor(n_cores / 2.0))
print "n_cores =", n_cores, "n_pops =", n_pops
spike_times = range(0, n_pops * spike_gap, spike_gap)
run_time = (n_pops + 1) * spike_gap + 1
for do_injector_first in [True, False]:
# Set up for execution
p.setup(1.0, machine=hostname)
injectors = list()
for i in range(n_pops):
injector = None
(x1, y1, p1) = cores[i * 2]
(x2, y2, p2) = cores[(i * 2) + 1]
if do_injector_first:
injector = create_injector(i, x1, y1, p1)
else:
injector = create_injector(i, x2, y2, p2)
injectors.append(injector)
populations = list()
for i in range(n_pops):
pop = None
cm = cm*area*1000 # convert to nF
Rm = 1e-6/(g_leak*area) # membrane resistance in MΩ
assert tau_m == cm*Rm # just to check
n_exc = int(round((n*r_ei/(1+r_ei)))) # number of excitatory cells
n_inh = n - n_exc # number of inhibitory cells
celltype = sim.IF_curr_exp
w_exc = 1e-3*Gexc*(Erev_exc - v_mean) # (nA) weight of excitatory synapses
w_inh = 1e-3*Ginh*(Erev_inh - v_mean) # (nA)
assert w_exc > 0; assert w_inh < 0
# === Build the network ========================================================
extra = {'threads' : threads,
'label': 'VA'}
node_id = sim.setup(timestep=dt, min_delay=delay, max_delay=delay, **extra)
print "%s Initialising the simulator with %d thread(s)..." % (node_id, extra['threads'])
cell_params = {
'tau_m' : tau_m, 'tau_syn_E' : tau_exc, 'tau_syn_I' : tau_inh,
'v_rest' : E_leak, 'v_reset' : v_reset, 'v_thresh' : v_thresh,
'cm' : cm, 'tau_refrac' : t_refrac}
print "%s Creating cell populations..." % node_id
exc_cells = sim.Population(n_exc, celltype, cell_params,
label="Excitatory_Cells")
inh_cells = sim.Population(n_inh, celltype, cell_params,
label="Inhibitory_Cells")
print "%s Initialising membrane potential to random values..." % node_id
This example requires that the NeuroTools package is installed
(http://neuralensemble.org/trac/NeuroTools)
Authors : Catherine Wacongne < *****@*****.** >
Xavier Lagorce < *****@*****.** >
April 2013
"""
import numpy, pylab, random, sys
import NeuroTools.signals as nt
import pyNN.spiNNaker as sim
# SpiNNaker setup
sim.setup(timestep=1.0,min_delay=1.0,max_delay=10.0, db_name='stdp_example.sqlite')
# +-------------------------------------------------------------------+
# | General Parameters |
# +-------------------------------------------------------------------+
# Population parameters
model = sim.IF_cond_exp
cell_params = {
'cm' : 0.281, # membrane capacitance nF
'e_rev_E' : 0.0, # excitatory reversal potential in mV
'e_rev_I' : -80.0, # inhibitory reversal potential in mV
'i_offset' : 0.0, # offset current
'tau_m' : 9.3667, # membrane time constant
'tau_refrac' : 0.1, # absolute refractory period
'tau_syn_E' : 5.0, # excitatory synaptic time constant
"""
Synfirechain-like example
Expected results in
.. figure:: ./examples/results/synfire_chain_lif.png
"""
#!/usr/bin/python
import pyNN.spiNNaker as p
import numpy, pylab
p.setup(timestep=1.0, min_delay = 1.0, max_delay = 8.0, db_name='synfire.sqlite')
n_pop = 16 # number of populations
nNeurons = 10 # number of neurons in each population
p.get_db().set_number_of_neurons_per_core('IF_curr_exp', nNeurons) # this will set one population per core
# random distributions
rng = p.NumpyRNG(seed=28374)
delay_distr = p.RandomDistribution('uniform', [1,10], rng=rng)
weight_distr = p.RandomDistribution('uniform', [0,2], rng=rng)
v_distr = p.RandomDistribution('uniform', [-55,-95], rng)
cell_params_lif_in = { 'tau_m' : 32,
'v_init' : -80,
'v_rest' : -75,
'v_reset' : -95,
"""
Synfirechain-like example
Expected results in
.. figure:: ./examples/results/synfire_chain_lif.png
"""
#!/usr/bin/python
import pyNN.spiNNaker as p
import numpy, pylab
p.setup(timestep=1.0, min_delay=1.0, max_delay=8.0, db_name='synfire.sqlite')
n_pop = 16 # number of populations
nNeurons = 10 # number of neurons in each population
p.get_db().set_number_of_neurons_per_core(
'IF_curr_exp', nNeurons) # this will set one population per core
# random distributions
rng = p.NumpyRNG(seed=28374)
delay_distr = p.RandomDistribution('uniform', [1, 10], rng=rng)
weight_distr = p.RandomDistribution('uniform', [0, 2], rng=rng)
v_distr = p.RandomDistribution('uniform', [-55, -95], rng)
cell_params_lif_in = {
'tau_m': 32,
'v_init': -80,
'v_rest': -75,
'v_reset': -95,
'v_thresh': -55,
$ ./stdp_example
This example requires that the NeuroTools package is installed
(http://neuralensemble.org/trac/NeuroTools)
Authors : Catherine Wacongne < *****@*****.** >
Xavier Lagorce < *****@*****.** >
April 2013
"""
import pylab
import pyNN.spiNNaker as sim
# SpiNNaker setup
sim.setup(timestep=1.0, min_delay=1.0, max_delay=10.0)
# +-------------------------------------------------------------------+
# | General Parameters |
# +-------------------------------------------------------------------+
# Population parameters
model = sim.IF_curr_exp
cell_params = {'cm': 0.25,
'i_offset': 0.0,
'tau_m': 20.0,
'tau_refrac': 2.0,
'tau_syn_E': 5.0,
'tau_syn_I': 5.0,
'v_reset': -70.0,
Each population has 256 neurons (4 neurons x 64 channels). Neurons in each population (ear) are numbered from 0 to 255, where:: id = ( channel * 4 ) + neuron .. moduleauthor:: Francesco Galluppi, SpiNNaker Project, [email protected] """ from pyNN.utility import get_script_args from pyNN.errors import RecordingError import pyNN.spiNNaker as p p.setup(timestep=1.0,min_delay=1.0,max_delay=10.0, db_name='cochlea_example.sqlite') nNeurons = 4 * 64 # 4 neurons and 64 channels per ear p.get_db().set_number_of_neurons_per_core('IF_curr_exp', nNeurons) # this will set 256 neurons per core cell_params = { 'i_offset' : .1, 'tau_refrac' : 3.0, 'v_rest' : -65.0, 'v_thresh' : -51.0, 'tau_syn_E' : 2.0, 'tau_syn_I': 5.0, 'v_reset' : -70.0, 'e_rev_E' : 0., 'e_rev_I' : -80.} left_cochlea_ear = p.Population(nNeurons, p.ProxyNeuron, {'x_source':254, 'y_source':254}, label='left_cochlea_ear') left_cochlea_ear.set_mapping_constraint({'x':0, 'y':0}) left_cochlea_ear.record() # this should record spikes from the cochlea
import matplotlib.pyplot as plt
import matplotlib.gridspec as gs
import os
#import pyNN.nest as pynn
import pyNN.spiNNaker as pynn
#set sim parameters
sim_time = 150
dt = 0.1
refrac = 0
start_test=78
end_test= 84
print("trials from "+str(start_test)+ "to "+str(end_test)
pynn.setup(dt)
pynn.set_number_of_neurons_per_core(pynn.IF_curr_exp, 64)
weight_scale = 1
rescale_fac = 1000/(1000*dt)
#load data
test_data = np.load("x_test.npz")['arr_0'][start_test:end_test]
test_labels = np.load("y_test.npz")['arr_0'][start_test:end_test]
pred_labels = []
#create network
network = []
#cell defaults
"""
Synfirechain-like example
"""
import pyNN.spiNNaker as p
import pylab
import numpy
p.setup(timestep=1.0, min_delay=1.0, max_delay=144.0)
nNeurons = 200 # number of neurons in each population
p.set_number_of_neurons_per_core("IF_curr_exp", nNeurons / 2)
runtime = 1000
cell_params_lif = {'cm': 0.25,
'i_offset': 0.0,
'tau_m': 20.0,
'tau_refrac': 2.0,
'tau_syn_E': 5.0,
'tau_syn_I': 5.0,
'v_reset': -70.0,
'v_rest': -65.0,
'v_thresh': -50.0
}
populations = list()
projections = list()
weight_to_spike = 2.0
delay = 17
loopConnections = list()
for i in range(0, nNeurons):
def run_sim(self):
"""
Sets up and runs the simulation
"""
num_neurons = 1471 # total neurons in network
num_inputs = 14 # number of neurons considered inputs
num_runs = 1 # number of times to loop the learning
num_samples = 1 # number of samples to learn`
sim_time = 1000.0 # time to run sim for`
inhibitory_split = 0.2
connection_probability_factor = 0.02
plot_spikes = True
save_figures = True
show_figures = True
sim_start_time = strftime("%Y-%m-%d_%H:%M")
cell_params_lif = {'cm': 0.25, 'i_offset': 0.0, 'tau_m': 10.0, 'tau_refrac': 2.0, 'tau_syn_E': 3.0,
'tau_syn_I': 3.0, 'v_reset': -65.0, 'v_rest': -65.0, 'v_thresh': -50.0}
# Create the 3d structure of the NeuCube based on the user's given structure file
network_structure = NetworkStructure()
network_structure.load_structure_file()
network_structure.load_input_location_file()
# Calculate the inter-neuron distance to be used in the small world connections
network_structure.calculate_distances()
# Generate two connection matrices for excitatory and inhibitory neurons based on your defined split
network_structure.calculate_connection_matrix(inhibitory_split, connection_probability_factor)
# Get these lists to be used when connecting the neurons later
excitatory_connection_list = network_structure.get_excitatory_connection_list()
inhibitory_connection_list = network_structure.get_inhibitory_connection_list()
# Choose the correct neurons to connect them to, based on your a-priori knowledge of the data source -- eg, EEG
# to 10-20 locations, fMRI to voxel locations, etc.
input_neuron_indexes = network_structure.find_input_neurons()
# Make the input connections based on this new list
input_weight = 4.0
input_connection_list = []
for index, input_neuron_index in enumerate(input_neuron_indexes):
input_connection_list.append((index, input_neuron_index, input_weight, 0))
for run_number in xrange(num_runs):
excitatory_weights = []
inhibitory_weights = []
for sample_number in xrange(num_samples):
# At the moment with the limitations of the SpiNNaker hardware we have to reinstantiate EVERYTHING
# each run. In future there will be some form of repetition added, where the structure stays in memory
# on the SpiNNaker and only the input spikes need to be updated.
data_prefix = sim_start_time + "_r" + str(run_number + 1) + "-s" + str(sample_number + 1)
# Set up the hardware - min_delay should never be less than the timestep.
# Timestep should = 1.0 (ms) for normal realtime applications
p.setup(timestep=1.0, min_delay=1.0)
p.set_number_of_neurons_per_core("IF_curr_exp", 100)
# Create a population of neurons for the reservoir
neurons = p.Population(num_neurons, p.IF_curr_exp, cell_params_lif, label="Reservoir")
# Setup excitatory STDP
timing_rule_ex = p.SpikePairRule(tau_plus=20.0, tau_minus=20.0)
weight_rule_ex = p.AdditiveWeightDependence(w_min=0.1, w_max=1.0, A_plus=0.02, A_minus=0.02)
stdp_model_ex = p.STDPMechanism(timing_dependence=timing_rule_ex, weight_dependence=weight_rule_ex)
# Setup inhibitory STDP
timing_rule_inh = p.SpikePairRule(tau_plus=20.0, tau_minus=20.0)
weight_rule_inh = p.AdditiveWeightDependence(w_min=0.0, w_max=0.6, A_plus=0.02, A_minus=0.02)
stdp_model_inh = p.STDPMechanism(timing_dependence=timing_rule_inh, weight_dependence=weight_rule_inh)
# record the spikes from that population
neurons.record('spikes')
# Generate a population of SpikeSourceArrays containing the encoded input spike data
# eg. spike_sources = p.Population(14, p.SpikeSourceArray, {'spike_times': [[]]})
# for the moment I'm going to cheat and just use poisson trains as I don't have data with me
spike_sources = p.Population(num_inputs, p.SpikeSourcePoisson, {'rate': rand.randint(20, 80)},
label="Poisson_pop_E")
# Connect the input spike sources with the "input" neurons
connected_inputs = p.Projection(spike_sources, neurons, p.FromListConnector(input_connection_list))
# If we have weights saved/recorded from a previous run of this network, load them into the structure
# population.set(weights=weights_list) and population.setWeights(weight_list) are not supported in
# SpiNNaker at the moment so we have to do this manually.
if excitatory_weights and inhibitory_weights:
for index, ex_connection in enumerate(excitatory_connection_list):
ex_connection[2] = excitatory_weights[index]
for index, in_connection in enumerate(inhibitory_connection_list):
in_connection[2] = inhibitory_weights[index]
# Setup the connectors
excitatory_connector = p.FromListConnector(excitatory_connection_list)
inhibitory_connector = p.FromListConnector(inhibitory_connection_list)
# Connect the excitatory and inhibitory neuron populations
connected_excitatory_neurons = p.Projection(neurons, neurons, excitatory_connector,
synapse_dynamics=p.SynapseDynamics(slow=stdp_model_ex),
target="excitatory")
connected_inhibitory_neurons = p.Projection(neurons, neurons, inhibitory_connector,
synapse_dynamics=p.SynapseDynamics(slow=stdp_model_inh),
target="inhibitory")
# Set up recording the spike trains of all the neurons
neurons.record()
spike_sources.record()
# Run the actual simulation
p.run(sim_time)
# Save the output spikes
spikes_out = neurons.getSpikes(compatible_output=True)
input_spikes_out = spike_sources.getSpikes(compatible_output=True)
# Get the synaptic weights of all the neurons
excitatory_weights = connected_excitatory_neurons.getWeights()
inhibitory_weights = connected_inhibitory_neurons.getWeights()
# when we're all done, clean up
p.end()
# Make some plots, save them if required. Check if you need to either save or show them, because if not,
# there's no point wasting time plotting things nobody will ever see.
if plot_spikes and (save_figures or show_figures):
plot = Plot(save_figures, data_prefix)
# Plot the 3D structure of the network
plot.plot_structure(network_structure.get_positions(), figure_number=0)
# Plot the spikes
plot.plot_spike_raster(spikes_out, sim_time, num_neurons, figure_number=1)
# Plot the weights
plot.plot_both_weights(excitatory_weights, inhibitory_weights, figure_number=2)
# If we want to show the figures, show them now, otherwise ignore and move on
if show_figures:
# Show them all at once
plot.show_plots()
plot.clear_figures()
plot = None
import pyNN.spiNNaker as p
import retina_lib
input_size = 128 # Size of each population
subsample_size = 32
runtime = 60
# Simulation Setup
p.setup(timestep=1.0, min_delay=1.0, max_delay=11.0) # Will add some extra parameters for the spinnPredef.ini in here
p.set_number_of_neurons_per_core("IF_curr_exp", 128) # this will set one population per core
cell_params = {
"tau_m": 64,
"i_offset": 0,
"v_rest": -75,
"v_reset": -95,
"v_thresh": -40,
"tau_syn_E": 15,
"tau_syn_I": 15,
"tau_refrac": 2,
}
# external stuff population requiremenets
connected_chip_coords = {"x": 0, "y": 0}
virtual_chip_coords = {"x": 0, "y": 5}
link = 4
print "Creating input population: %d x %d" % (input_size, input_size)
#!/usr/bin/env python
import IPython
import pyNN.spiNNaker as p
from pylab import *
nn_pre = 1000
nn_post = 16
nn_teach = 16 # neuron count
timestep = 0.6
duration = 100 * 1000
p.setup(timestep=timestep, min_delay=timestep, max_delay=10.0)
# p.set_number_of_neurons_per_core("IF_cond_exp", 12)
cell_params = {
"cm": 0.25, # nF
"i_offset": 0.0,
"tau_m": 10.0,
"tau_refrac": 2.0,
"tau_syn_E": 2.5,
"tau_syn_I": 2.5,
"v_reset": -70.0,
"v_rest": -65.0,
"v_thresh": -54.4,
}
cellparams_pclayer = {
"tau_refrac": 2.58198889747,
"tau_m": 40.343576523,
"e_rev_E": 0.0,
"cm": 0.645497224368,
"e_rev_I": -80.0,
def test_snn(randomness = False,
data_dir = "data/X_test_zied.npy",
cls_dir = "data/y_test_zied.npy",
data = "load", # pass data as argument
cls = "load"): # pass labels as argument
###############################################################################
## Function Definitions
###############################################################################
def gaussian(x, mu, sig):
return np.float16(np.exp(-np.power(x - mu, 2.) / (2 * np.power(sig, 2.))))
def calc_pop_code(feature, rng1, rng2, num):
interval = np.float(rng2 - rng1) / num
means = np.arange(rng1 + interval,rng2 + interval, interval)
pop_code = [gaussian(feature, mu, 0.025) for mu in means]
return pop_code
def PoissonTimes2(t_str=0., t_end=100., rate=10., seed=1.):
times = [t_str]
rng = np.random.RandomState(seed=seed)
cont = True
while cont == True:
t_next = np.floor(times[-1] + 1000. * next_spike_times(rng, rate))
if t_next < t_end - 30:
times.append(t_next[0])
else:
cont = False
return times[1:]
def PoissonTimes(t_str=0., t_end=100., rate=10., seed=1.):
if rate > 0:
interval = (t_end - t_str+0.) / rate
times = np.arange(t_str + 30, t_end - 40, interval)
return list(times)
else:
return []
def next_spike_times(rng,rate):
return -np.log(1.0 - rng.rand(1)) / rate
def ismember(a, b):
b = [b]
bind = {}
for i, elt in enumerate(b):
if elt not in bind:
bind[elt] = i
aa=[bind.get(itm, -1) for itm in a]
return sum(np.array(aa) + 1.)
###############################################################################
## Parameters
###############################################################################
# Load Parameter
parameters = np.load("output_files/parameters1.npy")
parameters = parameters.item()
# Load test data
if data == "load" and cls == "load":
data = np.load(data_dir)
cls = np.load(cls_dir)
# Simulation Parameters
trial_num = parameters["trial_num"] # How many samples (trials) from data will be presented
n_trials = len(cls)#10#20 #int(trial_num) # Total trials
time_int_trials = parameters["time_int_trials"] # (ms) Time to present each trial data
SIM_TIME = n_trials * time_int_trials # Total simulation time (ms)
ts = parameters["ts"] # Timestep of Spinnaker (ms)
min_del = ts
max_del = 144 * ts
p.setup(timestep=ts, min_delay=min_del, max_delay=max_del)
## Neuron Numbers
n_feature = parameters["n_feature"] # Number of features
n_pop = parameters["n_pop"] # Number of neurons in one population
n_cl = parameters["n_cl"] # Number of classes at the output
## Connection Parameters
# Weights
wei_src_enc = parameters["wei_src_enc"] # From Source Array at input to Encoding Layer(Exc)
wei_enc_filt = parameters["wei_enc_filt"] # From Encoding Layer to Filtering Layer Exc neurons (Exc)
wei_filt_inh = parameters["wei_filt_inh"] # From Filtering Layer Inh neurons to Exc neurons (Inh)
wei_cls_exc = parameters["wei_cls_exc"] # From Output Layer Exc neurons to Inh neurons (Exc)
wei_cls_inh = parameters["wei_cls_inh"] # From Output Layer Inh neurons to Exc neurons (Inh)
wei_noise_poi = parameters["wei_noise_poi"]
# Delays
del_src_enc = np.load("output_files/parameters2.npy")
del_enc_filt = parameters["del_enc_filt"]
del_init_stdp = parameters["del_init_stdp"]
del_cls_exc = parameters["del_cls_exc"]
del_cls_inh = parameters["del_cls_inh"]
del_noise_poi = parameters["del_noise_poi"]
# Firing Rates
noise_poi_rate = parameters["noise_poi_rate"]
max_fr_input = parameters["max_fr_input"] # maximum firing rate at the input layer
max_fr_rate_output = parameters["max_fr_rate_output"] # Maximum firing rate at output (supervisory signal)
## Connection Probabilities
prob_filt_inh = parameters["prob_filt_inh"] # Prob of connectivity inhi-connections at Filtering Layer
prob_stdp = parameters["prob_stdp"] # Probability of STDP connections
prob_output_inh = parameters["prob_output_inh"] # Prob of inhi-connections at Output Layer
prob_noise_poi_conn = parameters["prob_noise_poi_conn"]
## STDP Parameters
tau_pl = parameters["tau_pl"] #5
tau_min = tau_pl
stdp_w_max = parameters["stdp_w_max"]
stdp_w_min = parameters["stdp_w_min"]
stdp_A_pl = parameters["stdp_A_pl"]
stdp_A_min = -stdp_A_pl # minus in order to get symmetric curve
## Neuron Parameters
cell_params_lif = {'cm': 1.,
'i_offset': 0.0,
'tau_m': 20.,
'tau_refrac': 2.0,
'tau_syn_E': 5.0,
'tau_syn_I': 5.0,
'v_reset': -70.0,
'v_rest': -65.0,
'v_thresh': -65.0
}
###############################################################################
## Data Extraction
###############################################################################
## Extract Feature Data
scale_data = parameters["scale_data"] # Scale features into [0-scale_data] range
#data = np.load("features_without_artifact.npy")
#data = np.load('X_test.npy')
r, c = np.shape(data)
# Threshold (to keep spikes amplitudes in range)
thr_data_plus = parameters["thr_data_plus"]
thr_data_minus = parameters["thr_data_minus"]
data_rates = np.reshape(data, (1, r * c))[0]
# Shift an normalize the data
#dd = [d if d<thr_data_plus else thr_data_plus for d in data_rates]
#dd = [d if d>thr_data_minus else thr_data_minus for d in dd]
#dd2 = np.array(dd) - min(dd)
#dd2 = dd2 / max(dd2) * 2
dd2 = np.array(data_rates) - min(data_rates)
dd2 = dd2 / max(dd2) * 2
new_data_rates = []
for r in dd2:
new_data_rates += calc_pop_code(r, 0., scale_data,
n_feature / (n_pop + 0.0))
data_rates = list(max_fr_input * np.array(new_data_rates))
## Extract Class Data
#cls = np.load("classes_without_artifact.npy")
#cls = np.load("y_test.npy")
cls = cls.reshape(len(cls), 1)
r_cl, c_cl = np.shape(cls)
cls = list(np.reshape(cls, (1, r_cl * c_cl))[0])
outputs = cls[:n_trials]
poi_rate = data_rates[:n_feature * n_trials]
t1 = 0#70
t2 = int(t1 + n_trials)
outputs = cls[t1:t2]
poi_rate = data_rates[t1 * n_feature:n_feature * t2]
###############################################################################
## Create populations for different layers
###############################################################################
poi_layer = []
enc_layer = []
filt_layer_exc = []
out_layer_exc = []
out_layer_inh = []
# Calculate poisson spike times for features
spike_times = [[] for i in range(n_feature)]
for i in range(n_trials):
t_st = i * time_int_trials
t_end = t_st + time_int_trials
ind = i * n_feature
for j in range(n_feature):
times = PoissonTimes(t_st, t_end, poi_rate[ind+j],
np.random.randint(100))
for t in times:
spike_times[j].append(t)
if randomness == True: # if True: calculate "spike_times" (randomly) new
# if False: load previously saved "spike_times"
np.save('output_files/spike_times_test.npy', spike_times)
else:
spike_times = np.load('output_files/spike_times_test.npy')
# Spike source of input layer
spike_source = p.Population(n_feature,
p.SpikeSourceArray,
{'spike_times':spike_times},
label='spike_source')
enc_layer = p.Population(n_feature * n_pop,
p.IF_curr_exp,
cell_params_lif,
label='enc_layer')
filt_layer = p.Population(n_feature * n_pop,
p.IF_curr_exp,
cell_params_lif,
label='filt_layer')
#filt_layer_inh=p.Population(n_feature*n_pop, p.IF_curr_exp, cell_params_lif, label='filt_layer_inh')
for i in range(n_cl):
out_layer_exc.append(p.Population(n_pop,
p.IF_curr_exp,
cell_params_lif,
label='out_layer_exc{}'.format(i)))
out_layer_inh.append(p.Population(n_pop,
p.IF_curr_exp,
cell_params_lif,
label='out_layer_inh{}'.format(i)))
out_layer_exc[i].record()
poisson_input = p.Population(n_pop * 2,
p.SpikeSourcePoisson,
{"rate":noise_poi_rate})
enc_layer.record()
filt_layer.record()
###############################################################################
## Projections
###############################################################################
## Connection List from Spike Source Array to Encoding Layer
conn_inp_enc = np.load("output_files/conn_inp_enc.npy")
#Connection List for Filtering Layer Inhibitory
conn_filt_inh = np.load("output_files/conn_filt_inh.npy")
## STDP Connection List
conn_stdp_list = np.load("output_files/conn_stdp_list.npy")
diff_ind = np.load("output_files/diff_ind_filt.npy")
diff_ind2 = np.load("output_files/diff_ind_filt2.npy")
diff_thr2 = np.load("output_files/diff_thr2.npy")
c1 = 0
for cls_list in conn_stdp_list:
c2 = 0
cls_wei = np.load("output_files/stdp_weights{}.npy".format(c1))
mx = max(cls_wei)
for conn in cls_list:
# if ismember(diff_ind,conn[0]):
if (ismember(diff_ind2,conn[0]) and
np.sign(c1-0.5) * np.sign(diff_thr2[int(conn[0])]) == -1.):
# conn[2]=0.08*cls_wei[c2]/mx
conn[2] = 0.08#*diff_thr2[conn[0]]/36.
# conn[2]=2.*cls_wei[c2]
c2 += 1
c1 += 1
conn_stdp_list = list(conn_stdp_list)
## Output Layer Inhibitory Connection List
conn_output_inh = np.load("output_files/conn_output_inh.npy")
## Spike Source to Encoding Layer
p.Projection(spike_source,enc_layer,p.FromListConnector(conn_inp_enc))
## Encoding Layer to Filtering Layer
p.Projection(enc_layer, filt_layer,
p.OneToOneConnector(weights=wei_enc_filt,
delays=del_enc_filt))
## Filtering Layer Inhibitory
p.Projection(filt_layer,filt_layer,
p.FromListConnector(conn_filt_inh),
target="inhibitory")
## STDP Connection between Filtering Layer and Output Layer
stdp_proj = []
for j in range(n_cl):
stdp_proj.append(p.Projection(filt_layer, out_layer_exc[j],
p.FromListConnector(conn_stdp_list[j])))
## Connection between Output Layer neurons
c = 0
for i in range(n_cl):
p.Projection(out_layer_exc[i], out_layer_inh[i],
p.OneToOneConnector(weights=wei_cls_exc,
delays=del_cls_exc))
iter_array = [j for j in range(n_cl) if j != i]
for j in iter_array:
p.Projection(out_layer_inh[i], out_layer_exc[j],
p.FromListConnector(conn_output_inh[c]),
target="inhibitory")
c+=1
## Noisy poisson connection to encoding layer
if randomness == True: # if True: connect noise to network
# if False: don't use noise in network
p.Projection(poisson_input,
enc_layer,
p.FixedProbabilityConnector(p_connect=prob_noise_poi_conn,
weights=wei_noise_poi,
delays = del_noise_poi))
###############################################################################
## Simulation
###############################################################################
p.run(SIM_TIME)
Enc_Spikes = enc_layer.getSpikes()
Filt_Exc_Spikes = filt_layer.getSpikes()
#Filt_Inh_Spikes = filt_layer_inh.getSpikes()
Out_Spikes = [[] for i in range(n_cl)]
for i in range(n_cl):
Out_Spikes[i] = out_layer_exc[i].getSpikes()
p.end()
###############################################################################
## Plot
###############################################################################
## Plot 1
if 0:
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron ID')
pylab.title('Encoding Layer Raster Plot')
pylab.hold(True)
pylab.plot([i[1] for i in Enc_Spikes], [i[0] for i in Enc_Spikes], ".b")
pylab.hold(False)
#pylab.axis([-10,c*SIM_TIME+100,-1,numInp+numOut+numInp+3])
pylab.show()
## Plot 2-1
if 0:
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron ID')
pylab.title('Filtering Layer Raster Plot')
pylab.plot([i[1] for i in Filt_Exc_Spikes], [i[0] for i in Filt_Exc_Spikes], ".b")
#pylab.axis([-10,c*SIM_TIME+100,-1,numInp+numOut+numInp+3])
pylab.show()
## Plot 2-2
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron ID')
pylab.title('Filtering Layer Raster Plot')
pylab.hold(True)
pylab.plot([i[1] for i in Filt_Exc_Spikes], [i[0] for i in Filt_Exc_Spikes], ".b")
time_ind=[i*time_int_trials for i in range(len(outputs))]
for i in range(len(time_ind)):
pylab.plot([time_ind[i],time_ind[i]],[0,2000],"r")
pylab.hold(False)
#pylab.axis([-10,c*SIM_TIME+100,-1,numInp+numOut+numInp+3])
pylab.show()
## Plot 3-1
if 0:
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron ID')
pylab.title('Association Layer Raster Plot\nTest for Trial Numbers {}-{}'.format(t1,t2))
pylab.hold(True)
c=0
for array in Out_Spikes:
pylab.plot([i[1] for i in array], [i[0]+c for i in array], ".b")
c+=0.2
time_cls=[j*time_int_trials+i for j in range(len(outputs)) for i in range(int(time_int_trials))]
cls_lb=[outputs[j]+0.4 for j in range(len(outputs)) for i in range(int(time_int_trials))]
time_ind=[i*time_int_trials for i in range(len(outputs))]
for i in range(len(time_ind)):
pylab.plot([time_ind[i],time_ind[i]],[0,10],"r")
#pylab.plot(time_cls,cls_lb,".")
pylab.hold(False)
pylab.axis([-10,SIM_TIME+100,-1,n_pop+2])
pylab.show()
## Plot 3-2
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron ID')
pylab.title(('Association Layer Raster Plot\n',
'Test for Samples {}-{}').format(t1,t2))
pylab.hold(True)
pylab.plot([i[1] for i in Out_Spikes[0]],
[i[0] for i in Out_Spikes[0]],
".b")
pylab.plot([i[1] for i in Out_Spikes[1]],
[i[0] + 0.2 for i in Out_Spikes[1]],
".r")
time_ind = [i * time_int_trials for i in range(len(outputs))]
for i in range(len(time_ind)):
pylab.plot([time_ind[i], time_ind[i]], [0,n_pop], "k")
#pylab.plot(time_cls,cls_lb,".")
pylab.hold(False)
pylab.axis([-10, SIM_TIME+100, -1, n_pop + 2])
pylab.legend(["AN1","AN2" ])
pylab.show()
sum_output = [[] for i in range(n_cl)]
for i in range(n_trials):
t_st = i * time_int_trials
t_end = t_st + time_int_trials
for j in range(n_cl):
sum_output[j].append(np.sum(
[1 for n, t in Out_Spikes[j] if t >= t_st and t < t_end])
)
## Plot 4
if 0:
# pylab.figure()
# pylab.hold(True)
# pylab.plot(sum_output[0], "b.")
# pylab.plot(sum_output[1], "r.")
# out_cl0 = [i for i in range(len(outputs)) if outputs[i] == 0]
# out_cl1 = [i for i in range(len(outputs)) if outputs[i] == 1]
# pylab.plot(out_cl0,[-2 for i in range(len(out_cl0))], "xb")
# pylab.plot(out_cl1,[-2 for i in range(len(out_cl1))], "xr")
# pylab.hold(False)
# pylab.title("Total spikes at each AN population for each trial")
# pylab.xlabel("Trials")
# pylab.ylabel("Firing Rate")
# pylab.legend(["Cl0","Cl1","Winning Cl 0", "Winning Cl 1"])
# pylab.axis([-2, n_trials + 2, -4, max(max(sum_output)) + 30])
# pylab.show()
pylab.figure()
pylab.hold(True)
pylab.plot(sum_output[0], "b^")
pylab.plot(sum_output[1], "r^")
#pylab.plot(sum_output[0],"b")
#pylab.plot(sum_output[1],"r")
ppp0 = np.array(sum_output[0])
ppp1 = np.array(sum_output[1])
out_cl0 = [i for i in range(len(outputs)) if outputs[i] == 0]
out_cl1 = [i for i in range(len(outputs)) if outputs[i] == 1]
pylab.plot(out_cl0, ppp0[out_cl0], "bs")
pylab.plot(out_cl1, ppp1[out_cl1], "rs")
pylab.hold(False)
pylab.title("Total spikes at each AN population for each trial")
pylab.xlabel("Trials")
pylab.ylabel("Spike Count for Each Trial")
pylab.legend(["Cls 0", "Cls 1", "Actual Winner Cls 0",
"Actual Winner Cls 1"])
pylab.axis([-2, n_trials + 2, -4, max(max(sum_output)) + 30])
pylab.show()
## Check Classification rate
s = np.array(sum_output)
cl = np.floor((np.sign(s[1] - s[0]) + 1) / 2)
r_cl = np.array(outputs)
wrong = np.sum(np.abs(cl - r_cl))
rate = (n_trials - wrong) / n_trials
print("success rate: {}%".format(abs(rate)*100.))
print("cl:\n", cl)
print("r_cl:\n", r_cl)
## Plot 5
if 0:
pylab.figure()
cf = 0.1
pylab.hold(True)
cls_wei0 = np.load("output_files/stdp_weights{}.npy".format(0))
mx = max(cls_wei0)
cls_wei0 = cf * cls_wei0 / mx
cls_wei1 = np.load("output_files/stdp_weights{}.npy".format(1))
mx = max(cls_wei1)
cls_wei1 = cf * cls_wei1/ mx
l = min(len(cls_wei0), len(cls_wei1))
new_array0 = [cls_wei0[i] for i in range(l) if cls_wei0[i] > cls_wei1[i]]
x0 = [i for i in range(l) if cls_wei0[i] > cls_wei1[i]]
new_array1 = [cls_wei1[i] for i in range(l) if cls_wei1[i] > cls_wei0[i]]
x1 = [i for i in range(l) if cls_wei1[i] > cls_wei0[i]]
pylab.plot(x0, new_array0, "gx")
pylab.plot(x1, new_array1, "bx")
#for i in range(2):
# cls_wei=np.load("stdp_weights{}.npy".format(i))
# mx=max(cls_wei)
# cls_wei=0.05*cls_wei/mx
# pylab.plot(cls_wei,"x")
pylab.axis([-10, 2000, -0.1, 0.15])
pylab.hold(False)
pylab.show()
## Plot 7
if 0:
sum_filt = [[0 for i in range(n_feature * n_pop)] for j in range(n_cl)]
sum_filt = np.array(sum_filt)
for i in range(n_trials):
t_st = i * time_int_trials
t_end = t_st + time_int_trials
cl = outputs[i]
for n, t in Filt_Exc_Spikes:
if t >= t_st and t < t_end:
sum_filt[int(cl),int(n)] = sum_filt[(cl),int(n)] + 1
a4=sum_filt[0]
b4=sum_filt[1]
pylab.figure()
pylab.hold(True)
pylab.plot(a4,"b.")
pylab.plot(b4,"r.")
pylab.xlabel('Neuron ID')
pylab.ylabel('Total Firing Rates Through Trials')
pylab.title("Total Spiking Activity of Neurons at Decomposition Layer for Each Class")
pylab.hold(False)
pylab.legend(["Activity to AN1","Activity to AN2"])
pylab.show()
return rate
tau_m = 20. # (ms)
cm = 1. # (uF/cm^2)
g_leak = 5e-5 # (S/cm^2)
E_leak = -60 # (mV)
v_thresh = -50. # (mV)
v_reset = -60. # (mV)
t_refrac = 10. # (ms) (clamped at v_reset)
tau_exc = 5. # (ms)
tau_inh = 10. # (ms)
cell_params = {
'tau_m' : tau_m, 'tau_syn_E' : tau_exc, 'tau_syn_I' : tau_inh,
'v_rest' : E_leak, 'v_reset' : v_reset, 'v_thresh' : v_thresh,
'cm' : cm, 'tau_refrac' : t_refrac}
############################### setup simulation
sim.setup(timestep=dt, min_delay=1.0)
# build populations
cell_type = sim.IF_cond_exp
num_of_cells = 10
layers = 10
populations = []
for i in range(layers):
curr_pop = sim.Population(num_of_cells, cell_type, cell_params, label="Population {0}".format(i))
populations.append(curr_pop)
curr_pop.initialize('v', v_reset)
if mode == "spikes":
populations[-1].record()
else:
populations[0].record_v()
import pyNN.spiNNaker as p
INJECTOR_LABEL = "injector"
RECEIVER_LABEL = "receiver"
# declare python code when received spikes for a timer tick
def receive_spikes(label, time, neuron_ids):
for neuron_id in neuron_ids:
print("Received spike at time {} from {}-{}"
"".format(time, label, neuron_id))
p.setup(timestep=1.0)
p1 = p.Population(1, p.IF_curr_exp(), label="pop_1")
input_injector = p.Population(1, p.external_devices.SpikeInjector(),
label=INJECTOR_LABEL)
# set up python live spike connection
live_spikes_connection = p.external_devices.SpynnakerLiveSpikesConnection(
receive_labels=[RECEIVER_LABEL])
# register python receiver with live spike connection
live_spikes_connection.add_receive_callback(RECEIVER_LABEL, receive_spikes)
input_proj = p.Projection(input, p1, p.OneToOneConnector(),
p.StaticSynapse(weight=5, delay=3))
p1.record(["spikes", "v"])
p.run(50)
import pyNN.spiNNaker as p
from matplotlib import pylab
p.setup(timestep=1.0)
input_pop = p.Population(1, p.SpikeSourceArray, cellparams={"spike_times": [0]},
label="input")
cell_params_lif = {'cm' : 0.25, # nF
'i_offset' : 0.0,
'tau_m' : 20.0,
'tau_refrac': 2.0,
'tau_syn_E' : 5.0,
'tau_syn_I' : 5.0,
'v_reset' : -70.0,
'v_rest' : -65.0,
'v_thresh' : -50.0
}
pop = p.Population(2, p.IF_curr_exp, cellparams=cell_params_lif, label="pop")
connections = list()
connections.append(p.Projection(input_pop, pop, p.AllToAllConnector(weights=[0.3, 1.0], delays=[1, 17])))
connections.append(p.Projection(input_pop, pop, p.AllToAllConnector(weights=[1.0, 0.7], delays=[2, 15])))
connections.append(p.Projection(input_pop, pop, p.AllToAllConnector(weights=[0.7, 0.3], delays=[3, 33])))
pre_weights = list()
pre_delays = list()
for connection in connections:
pre_weights.append(connection.getWeights())
pre_delays.append(connection.getDelays())
p.run(100)
post_weights = list()
import pyNN.spiNNaker as p
import pylab
import numpy
from pyNN.random import RandomDistribution
p.setup(timestep=0.1)
n_neurons = 1000
n_exc = int(round(n_neurons * 0.8))
n_inh = int(round(n_neurons * 0.2))
weight_exc = 0.1
weight_inh = -5.0 * weight_exc
pop_exc = p.Population(n_exc, p.IF_curr_exp, {}, label="Excitatory")
pop_inh = p.Population(n_inh, p.IF_curr_exp, {}, label="Inhibitory")
stim_exc = p.Population(n_exc, p.SpikeSourcePoisson, {"rate": 1000.0}, label="Stim_Exc")
stim_inh = p.Population(n_inh, p.SpikeSourcePoisson, {"rate": 1000.0}, label="Stim_Inh")
delays_exc = RandomDistribution("normal", [1.5, 0.75], boundaries=(1.0, 14.4))
weights_exc = RandomDistribution("normal", [weight_exc, 0.1], boundaries=(0, numpy.inf))
conn_exc = p.FixedProbabilityConnector(0.1, weights=weights_exc, delays=delays_exc)
delays_inh = RandomDistribution("normal", [0.75, 0.375], boundaries=(1.0, 14.4))
weights_inh = RandomDistribution("normal", [weight_inh, 0.1], boundaries=(-numpy.inf, 0))
conn_inh = p.FixedProbabilityConnector(0.1, weights=weights_inh, delays=delays_inh)
p.Projection(pop_exc, pop_exc, conn_exc, target="excitatory")
p.Projection(pop_exc, pop_inh, conn_exc, target="excitatory")
p.Projection(pop_inh, pop_inh, conn_inh, target="inhibitory")
p.Projection(pop_inh, pop_exc, conn_inh, target="inhibitory")
conn_stim = p.OneToOneConnector(weights=weight_exc, delays=1.0)
p.Projection(stim_exc, pop_exc, conn_stim, target="excitatory")
p.Projection(stim_inh, pop_inh, conn_stim, target="excitatory")
'''' THIS CODE TRIES TO IMPLEMENT THE LAST APPLICATION FROM NESSLER'S STDP-EM PAPER'''
Neurons=int(raw_input('Enter the total No.Of neurons(700) in the simulation: '))
n= int(raw_input('Enter No of Patterns you totally want(n): '))
pattern_gap= int(raw_input('Enter the duration after which next pattern should appear(pattern_gap) 250: '))
k=int(raw_input('Enter the pattern length, for now give 50)(k): '))
weight_to_spike=1.0
import pyNN.spiNNaker as p
import pylab
import pickle
import numpy as np
p.setup(timestep = 1.0) # runs using a 1.0ms timestep
# here the default parameters of the IF_curr_exp are used. These are:
# In PyNN, the neurons are declared in terms of a population of a number of neurons with similar properties
cell_params_lif = {'cm' : 0.35, # nF #capacitance of LIF neuron in nF
'i_offset' : 0.0, #A base input current to add each timestep.(What current??)
'tau_m' : 4, #The time-constant of the RC circuit, in ms
'tau_refrac': 1, #The refractory period in ms
'tau_syn_E' : 1, #The excitatory input current decay time-constant
'tau_syn_I' : 10, #The inhibitory input current decay time-constant
'v_reset' : -70.6, #The voltage to set the neuron at immediately after a spike
'v_rest' : -65, #The ambient rest voltage of the neuron
'v_thresh' : -50. #The threshold voltage at which the neuron will spike.
}
################################################%%%%%%%%%%%%CONSTRUCTING THE PATTERN%%%%%%%%%%%############%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
b=pickle.load(open('/home/ruthvik/Desktop/spikefile_700_50ms_6Hz','rb'))
def train(spikeTimes,untrained_weights=None):
organisedStim = {}
labelSpikes = []
#spikeTimes = generate_data()
#for j in range(5):
# labelSpikes
#labelSpikes[label] = [(input_len-1)*v_co+1,(input_len-1)*v_co*2+1,(input_len-1)*v_co*3+1,]
if untrained_weights == None:
untrained_weights = RandomDistribution('uniform', low=wMin, high=wMaxInit).next(input_size*output_size)
#untrained_weights = RandomDistribution('normal_clipped', mu=0.1, sigma=0.05, low=wMin, high=wMaxInit).next(input_size*output_size)
untrained_weights = np.around(untrained_weights, 3)
#saveWeights(untrained_weights, 'untrained_weightssupmodel1traj')
print ("init!")
print "length untrained_weights :", len(untrained_weights)
if len(untrained_weights)>input_size:
training_weights = [[0 for j in range(output_size)] for i in range(input_size)] #np array? size 1024x25
k=0
for i in range(input_size):
for j in range(output_size):
training_weights[i][j] = untrained_weights[k]
k += 1
else:
training_weights = untrained_weights
connections = []
for n_pre in range(input_size): # len(untrained_weights) = input_size
for n_post in range(output_size): # len(untrained_weight[0]) = output_size; 0 or any n_pre
connections.append((n_pre, n_post, training_weights[n_pre][n_post], __delay__)) #index
runTime = int(max(max(spikeTimes))/3)+100
#####################
sim.setup(timestep=1)
#def populations
layer1=sim.Population(input_size,sim.SpikeSourceArray, {'spike_times': spikeTimes},label='inputspikes')
layer2=sim.Population(output_size,sim.IF_curr_exp,cellparams=cell_params_lif,label='outputspikes')
#supsignal=sim.Population(output_size,sim.SpikeSourceArray, {'spike_times': labelSpikes},label='supersignal')
#def learning rule
stdp = sim.STDPMechanism(
weight=untrained_weights,
#weight=0.02, # this is the initial value of the weight
#delay="0.2 + 0.01*d",
timing_dependence=sim.SpikePairRule(tau_plus=tauPlus, tau_minus=tauMinus,A_plus=aPlus, A_minus=aMinus),
#weight_dependence=sim.MultiplicativeWeightDependence(w_min=wMin, w_max=wMax),
weight_dependence=sim.AdditiveWeightDependence(w_min=wMin, w_max=wMax),
#weight_dependence=sim.AdditiveWeightDependence(w_min=0, w_max=0.4),
dendritic_delay_fraction=1.0)
#def projections
#stdp_proj = sim.Projection(layer1, layer2, sim.FromListConnector(connections), synapse_type=stdp)
stdp_proj = sim.Projection(layer1, layer2, sim.AllToAllConnector(), synapse_type=stdp)
inhibitory_connections = sim.Projection(layer2, layer2, sim.AllToAllConnector(allow_self_connections=False),
synapse_type=sim.StaticSynapse(weight=inhibWeight, delay=__delay__),
receptor_type='inhibitory')
#stim_proj = sim.Projection(supsignal, layer2, sim.OneToOneConnector(),
# synapse_type=sim.StaticSynapse(weight=stimWeight, delay=__delay__))
layer1.record(['spikes'])
layer2.record(['v','spikes'])
#supsignal.record(['spikes'])
sim.run(runTime)
print("Weights:{}".format(stdp_proj.get('weight', 'list')))
weight_list = [stdp_proj.get('weight', 'list'), stdp_proj.get('weight', format='list', with_address=False)]
neo = layer2.get_data(["spikes", "v"])
spikes = neo.segments[0].spiketrains
v = neo.segments[0].filter(name='v')[0]
#neostim = supsignal.get_data(["spikes"])
#spikestim = neostim.segments[0].spiketrains
neoinput= layer1.get_data(["spikes"])
spikesinput = neoinput.segments[0].spiketrains
plt.close('all')
pplt.Figure(
pplt.Panel(spikesinput,xticks=True, yticks=True, markersize=2, xlim=(0,runTime),xlabel='(a) Spikes of Input Layer'),
#pplt.Panel(spikestim, xticks=True, yticks=True, markersize=2, xlim=(0,runTime),xlabel='(c) Spikes of Supervised Layer'),
pplt.Panel(spikes, xticks=True, xlabel="(b) Spikes of Output Layer", yticks=True, markersize=2, xlim=(0,runTime)),
pplt.Panel(v, ylabel="Membrane potential (mV)", xticks=True, yticks=True, xlim=(0,runTime),xlabel='(c) Membrane Potential of Output Layer\nTime (ms)'),
title="Two Training",
annotations="Twoway Training"
).save('SNN_DVS_un/plot_for_twoway/'+str(trylabel)+'_training.png')
#plt.hist(weight_list[1], bins=100)
plt.close('all')
plt.hist([weight_list[1][0:input_size], weight_list[1][input_size:input_size*2], weight_list[1][input_size*2:]], bins=20, label=['neuron 0', 'neuron 1', 'neuron 2'], range=(0, wMax))
plt.title('weight distribution')
plt.xlabel('Weight value')
plt.ylabel('Weight count')
#plt.show()
#plt.show()
sim.end()
return weight_list[1]
# helper function for populations
def get_pops(n_in_pop, n_used_neuronblocks=7):
l = []
model_type = pynn.IF_curr_exp
for _ in xrange(n_used_neuronblocks):
pop = pynn.Population(n_in_pop, model_type, params)
pop.record()
l.append(pop)
return l
pynn.setup(timestep=0.1)
duration = 1 * 3000 # ms
params = {"cm": 0.2, "v_reset": -70, "v_rest": -50, "v_thresh": -47}
n_in_pop = 12
# prepare populations
all_pops = []
all_pops.extend(get_pops(n_in_pop))
all_pops.extend(get_pops(n_in_pop))
# -> makes 14 population
# synaptic weight, must be tuned for spinnaker
w_exc = 0.25
#!/usr/bin/env python
import IPython
import pyNN.spiNNaker as p
from pylab import *
nn_pre = 1000
nn_post = 16
nn_teach = 16 # neuron count
timestep = 0.6
duration = 100 * 1000
p.setup(timestep=timestep, min_delay=timestep, max_delay=10.0)
#p.set_number_of_neurons_per_core("IF_cond_exp", 12)
cell_params = {
'cm': 0.25, # nF
'i_offset': 0.0,
'tau_m': 10.0,
'tau_refrac': 2.0,
'tau_syn_E': 2.5,
'tau_syn_I': 2.5,
'v_reset': -70.0,
'v_rest': -65.0,
'v_thresh': -54.4
}
cellparams_pclayer = {
'tau_refrac': 2.58198889747,
'tau_m': 40.343576523,
'e_rev_E': 0.0,
'cm': 0.645497224368,
'e_rev_I': -80.0,
import pylab
import numpy
from numpy.random import randint
from numpy import where
import time
import os
runtime = 10000
weight_to_spike = 3.
timestep = 1.
min_delay = 1.
max_delay = 20.
sim.setup(timestep=timestep, min_delay=min_delay, max_delay=max_delay)
max_weight = 10.
min_weight = 0.000001
a_plus = 0.1
a_minus = 0.12
tau = 20.
conn_prob = 10. / 100.
num_neurons = 200
cell_type = sim.IZK_curr_exp
exc_params = {
'a': 0.02,
import pyNN.spiNNaker as sim
import pyNN.utility.plotting as plot
import matplotlib.pyplot as plt
import threading
from random import uniform
from time import sleep
from pykeyboard import PyKeyboard
sim.setup(timestep=1.0)
sim.set_number_of_neurons_per_core(sim.IF_curr_exp, 100)
input1 = sim.Population(6,
sim.external_devices.SpikeInjector(),
label="stateSpikeInjector")
pre_pop = sim.Population(6,
sim.IF_curr_exp(tau_syn_E=100, tau_refrac=50),
label="statePopulation")
post_pop = sim.Population(1, sim.IF_curr_exp(), label="actorPopulation")
sim.external_devices.activate_live_output_for(pre_pop,
database_notify_host="localhost",
database_notify_port_num=19996)
sim.external_devices.activate_live_output_for(input1,
database_notify_host="localhost",
database_notify_port_num=19998)
timing_rule = sim.SpikePairRule(tau_plus=20.0,
tau_minus=20.0,
A_plus=0.5,
A_minus=0.5)
# ******************** NESIM-RT ******************** # # ----------------------------------------------------- # # A Real Time Spiking Neural Network Simulator # # ----------------------------------------------------- # # # # Author: Daniel Jesus Rosa Gallardo # # email: [email protected] # # Date: 2019 # # Cadiz University - Spain # # # ################################################################# import pyNN.spiNNaker as sim import pyNN.utility.plotting as plot import matplotlib.pyplot as plt sim.setup(timestep=0.25) cell_params_lif = { 'cm': 0.25, 'i_offset': 0, 'tau_m': 20, 'tau_refrac': 2, 'tau_syn_E': 50, 'tau_syn_I': 5, 'v_reset': -70, 'v_rest': -65, 'v_thresh': -55 } sim.set_number_of_neurons_per_core(sim.IF_curr_exp, 100)
"""
Synfirechain-like example
"""
import pyNN.spiNNaker as p
import pylab
import numpy
p.setup(timestep=1.0, min_delay=1.0, max_delay=144.0)
nNeurons = 200 # number of neurons in each population
p.set_number_of_neurons_per_core("IF_curr_exp", nNeurons / 2)
runtime = 1000
cell_params_lif = {'cm': 0.25,
'i_offset': 0.0,
'tau_m': 20.0,
'tau_refrac': 2.0,
'tau_syn_E': 5.0,
'tau_syn_I': 5.0,
'v_reset': -70.0,
'v_rest': -65.0,
'v_thresh': -50.0
}
populations = list()
projections = list()
weight_to_spike = 2.0
delay = 17
loopConnections = list()
for i in range(0, nNeurons):
:func:`NeuralModel.write_neural_c_file` and :func:`NeuralModel.write_neural_header_file` can be used to generate c code to be executed on SpiNNaker. .. moduleauthor:: Francesco Galluppi email: [email protected] """ import pacman import os import math import pyNN.spiNNaker as p import model_templates DEBUG = False dao = p.setup(db_name='/tmp/model_creator.db') FALSE = 0 TRUE = 1 ONE_PER_POPULATION = 2 class NeuralModel(): """ Initialises a new neural model: :param model_name: A string identifiying the Neural Model class in PyNN :type model_name: str. :param default_neurons_per_core: The default number of neurons of this type \ modelled by a single core :param image_name: (str) the name of the associated aplx image
AbstractOutgoingEdgeSameContiguousKeysRestrictor.__init__(self)
def get_outgoing_edge_constraints(self, partitioned_edge, graph_mapper):
constraints = AbstractOutgoingEdgeSameContiguousKeysRestrictor\
.get_outgoing_edge_constraints(
self, partitioned_edge, graph_mapper)
constraints.append(KeyAllocatorFixedKeyAndMaskConstraint(
[KeyAndMask(0x42000000, 0xFFFF0000)]))
return constraints
def is_virtual_vertex(self):
return True
def model_name(self):
return "My External Device"
import pyNN.spiNNaker as p
from pacman.model.partitionable_graph.multi_cast_partitionable_edge \
import MultiCastPartitionableEdge
p.setup(1.0)
device = p.Population(20, MyExternalDevice, {"spinnaker_link_id": 0},
label="external device")
pop = p.Population(20, p.IF_curr_exp, {}, label="population")
p.Projection(device, pop, p.OneToOneConnector())
p.run(10)
import pyNN.spiNNaker as pynn
# helper function for populations
def get_pops(n_in_pop, n_used_neuronblocks=7):
l = []
model_type = pynn.IF_cond_exp
for _ in xrange(n_used_neuronblocks):
pop = pynn.Population(n_in_pop, model_type, params)
pop.record()
l.append(pop)
return l
pynn.setup(timestep=1.0)
duration = 1 * 30000 # ms
params = {
'cm': 0.2,
'v_reset': -70,
'v_rest': -50,
'v_thresh': -47,
'e_rev_I': -60,
'e_rev_E': -40,
}
n_in_pop = 12
def train_snn(### Settings
data_dir = "data/X_train_zied.npy",
cls_dir = "data/y_train_zied.npy",
data = "load", # pass data as argument
cls = "load", # pass labels as argument
save = True, # True to save all parameters of the network
randomness = True,
reverse_src_del = False,
use_old_weights = False,
rand_data = False,
### Parameters
n_training = 2, # How many times the samples will be iterated
ts = 1., # Timestep of Spinnaker (ms)
trial_num = 10, # How many samples (trials) from data used
# Network
n_feature = 80, # Number of features (= 4 features * 20 neurons)
# Weights
wei_src_enc = .2, # From Source Array at input to Encoding Layer(Exc)
wei_enc_filt = .6, # From Encoding Layer to Filtering Layer Exc neurons (Exc)
wei_filt_inh = 0.03, # From Filtering Layer Inh neurons to Exc neurons (Inh)
wei_init_stdp = .0, # From Filtering Layer Exc neurons to Output Layer (Exc)
wei_cls_exc = 0.9, # From Output Layer Exc neurons to Inh neurons (Exc)
wei_cls_inh = 50,#0.1,#,10 # From Output Layer Inh neurons to Exc neurons (Inh)
wei_source_outp = 10., # From Source Array at output to Output Layer Exc neurons (Exc)
wei_noise_poi = 0.02,
# Delays
del_init_stdp = 1.,
del_source_outp = 1.,
del_noise_poi = 1.,
# Connection Probabilities
prob_filt_inh = .4, # Prob of connectivity inhibitory connections at FilT_Layer
prob_stdp = 1., # Prob of STDP connections
prob_output_inh = .7, # Prob of inhibitory connections at Output Layer
prob_noise_poi_conn = 0.02,
## STDP Parameters
tau_pl = 5.,
stdp_w_max = 0.4, # default 0.4
stdp_w_min = 0.0, # default 0.0
stdp_A_pl = 2,#0.02,# 0.01, # default 0.01 (below 0.01 weights don't change)
# => minus in order to get symmetric curve
# Data Extraction
scale_data = 2.): # Scale features into [0-scale_data] range
# BUG fix:
# n_feature is somehow a tuple
# try:
# trial_num = trial_num[0]
# except Exception as e:
# print("\n\n\n EXCEPTION TRIGGERED !!!! \n\n\n")
# pass
############################################################################
## Function Definitions
############################################################################
def gaussian(x, mu, sig):
return np.float16(np.exp(-np.power(x - mu, 2.) /
(2 * np.power(sig, 2.))))
def calc_pop_code(feature, rng1, rng2, num):
interval=np.float(rng2-rng1)/num
means=np.arange(rng1+interval, rng2+interval, interval)
pop_code=[gaussian(feature,mu,0.025) for mu in means]
return pop_code
def PoissonTimes2(t_str=0., t_end=100., rate=10., seed=1.):
times = [t_str]
rng = np.random.RandomState(seed=seed)
cont = True
while cont == True:
t_next = np.floor(times[-1] + 1000. * next_spike_times(rng,rate))
if t_next < t_end - 30:
times.append(t_next[0])
else:
cont=False
return times[1:]
def PoissonTimes(t_str=0., t_end=100., rate=10., seed=1., max_rate=0):
if rate>0:
interval = (t_end - t_str + 0.) / rate
# Add additional reverse_src_del
if reverse_src_del == True:
times = np.arange(t_str + 30, t_end - 40, interval)
# add reverse proportional delay
rev_del = np.ceil(max_rate / rate)
if rev_del != np.inf:
times += rev_del
else:
times = np.arange(t_str + 30, t_end - 40, interval)
return list(times)
else:
return []
def next_spike_times(rng,rate):
return -np.log(1.0-rng.rand(1)) / rate
def ismember(a, b):
b=[b]
bind = {}
for i, elt in enumerate(b):
if elt not in bind:
bind[elt] = i
aa=[bind.get(itm, -1) for itm in a]
return sum(np.array(aa)+1.)
def get_data(trial_num, test_num=10):
# trial_num: number of training samples
# test_num: number of test samples
pass
def rand_sample_of_train_set(n):
# n: number of features
# Return: np.array containing n samples of the training set
X = np.load(data_dir)
y = np.load(cls_dir)
idx = np.random.randint(len(X), size=n)
return X[idx], y[idx]
############################################################################
## Parameters
############################################################################
# Load training data
# only load n_rand_data features of training set
if rand_data == True:
data, cls = rand_sample_of_train_set(trial_num)
# load all features of training set
else: # load data if its not in passed as fuct argument
if data == "load" and cls == "load":
data = np.load(data_dir)
cls = np.load(cls_dir)
# Simulation Parameters
trial_num = len(cls) # How many samples (trials) from data will be presented
#n_training = 1 # How many times the samples will be iterated
n_trials = n_training * trial_num # Total trials
time_int_trials = 200. # (ms) Time to present each trial data
SIM_TIME = n_trials * time_int_trials # Total simulation time (ms)
#ts = 1. # Timestep of Spinnaker (ms)
min_del = ts
max_del = 144 * ts
p.setup(timestep=ts, min_delay=min_del, max_delay=max_del)
## Neuron Numbers
#n_feature = 80 # Number of features (= 4 features * 20 neurons)
# => 20 neuros: resolution of encoding
n_pop = data.shape[1] #4 # Number of neurons in one population (X dim)
n_cl = 2 # Number of classes at the output
## Connection Parameters
# Weights
# wei_src_enc = .2 # From Source Array at input to Encoding Layer(Exc)
# wei_enc_filt = .6 # From Encoding Layer to Filtering Layer Exc neurons (Exc)
# wei_filt_inh = 0.03 # From Filtering Layer Inh neurons to Exc neurons (Inh)
# wei_init_stdp = .0 # From Filtering Layer Exc neurons to Output Layer (Exc)
# wei_cls_exc = 0.9 # From Output Layer Exc neurons to Inh neurons (Exc)
# wei_cls_inh = 10 # 0.1 # From Output Layer Inh neurons to Exc neurons (Inh)
# wei_source_outp = 10. # From Source Array at output to Output Layer Exc neurons (Exc)
# wei_noise_poi = 0.02
# Delays
if randomness == True: # if True: calculate "del_src_enc" (randomly) new
# if False: load previously saved "del_src_enc"
if reverse_src_del == True:
# calc delays erversly proportional to feature value
del_src_enc = np.zeros(n_feature*n_pop)
else:
del_src_enc = [int(np.random.randint(n_pop)+1)
for _ in range(n_feature*n_pop)]
np.save("output_files/del_src_enc.npy", del_src_enc)
else:
#del_src_enc = np.load("output_files/del_src_enc.npy")
del_src_enc = np.ones(n_feature*n_pop).astype(int) #[1 for _ in range(n_feature*n_pop)]
del_enc_filt = ts
del_filt_inh = ts
# del_init_stdp = 1.
del_cls_exc = ts
del_cls_inh = ts
# del_source_outp = 1.
# del_noise_poi = 1.
# Firing Rates
noise_poi_rate = 10.
max_fr_input = 100. # maximum firing rate at the input layer
max_fr_rate_output = 20. # Maximum firing rate at output (supervisory signal)
## Connection Probabilities
# prob_filt_inh = .4 # Prob of connectivity inhibitory connections at FilT_Layer
# prob_stdp = 1. # Prob of STDP connections
# prob_output_inh = .7 # Prob of inhibitory connections at Output Layer
# prob_noise_poi_conn = 0.02
## STDP Parameters
# tau_pl = 0.3 # (0.2 - 0.3 works)
tau_min = tau_pl # default tau_pl
# stdp_w_max = 0.4 # default 0.4
# stdp_w_min = 0.0 # default 0.0
# stdp_A_pl = 0.01 # default 0.01 (below 0.01 weights don't change)
stdp_A_min = -stdp_A_pl # default - stdp_A_pl
# => minus in order to get symmetric curve
## Neuron Parameters
cell_params_lif = {'cm': 0.25,# 0.25,
'i_offset': 0.0,
'tau_m': 20.,
'tau_refrac': 2.0,
'tau_syn_E': 5.0,
'tau_syn_I': 5.0,
'v_reset': -70.0,
'v_rest': -65.0,
'v_thresh': -50#-50
}
############################################################################
## Data Extraction
############################################################################
## Extract Feature Data
# scale_data = 2. # Scale features into [0-scale_data] range
r,c = np.shape(data)
data_rates = np.reshape(data, (1, r*c))[0]
# Threshold (to keep spikes in range)
thr_data_plus = 30
thr_data_minus = -10
#dd = [d if d<thr_data_plus else thr_data_plus for d in data_rates]
#dd = [d if d>thr_data_minus else thr_data_minus for d in dd]
# Shift and normalize data
#dd2 = np.array(dd) - min(dd)
dd2 = np.array(data_rates) - min(data_rates)
dd2 = dd2 / max(dd2) * 2
new_data_rates = []
for r in dd2:
new_data_rates += calc_pop_code(r, 0., scale_data, n_feature /
(n_pop + 0.0))
data_rates = list(max_fr_input*np.array(new_data_rates))
## Extract Class Data
# load class vector
#cls = np.load(path_y)
cls = np.reshape(cls, (len(cls),1)) # create col vector
r_cl, c_cl = np.shape(cls)
#cls = list(np.reshape(cls, (1, r_cl * c_cl))[0] - 1)
cls = list(np.reshape(cls, (1, r_cl * c_cl))[0])
## The class and rate information to be used during the simulation
outputs = n_training * cls[0:trial_num] # positiv, ints
poi_rate = n_training * data_rates[0:trial_num * n_feature]
## Save parameters to be used in test
parameter_dict = {"n_feature":n_feature, "n_pop":n_pop,"n_cl":n_cl,
"wei_src_enc":wei_src_enc, "wei_enc_filt":wei_enc_filt,
"wei_filt_inh":wei_filt_inh, "wei_cls_exc":wei_cls_exc,
"wei_cls_inh":wei_cls_inh, "del_enc_filt":del_enc_filt,
"del_init_stdp":del_init_stdp, "del_cls_exc":del_cls_exc,
"del_cls_inh":del_cls_inh, "trial_num":trial_num,
"time_int_trials":time_int_trials, "scale_data":scale_data,
"ts":ts,"max_fr_input":max_fr_input,
"max_fr_rate_output":max_fr_rate_output,
"noise_poi_rate":noise_poi_rate, "max_fr_input":max_fr_input,
"max_fr_rate_output":max_fr_rate_output, "prob_filt_inh":prob_filt_inh,
"prob_stdp":prob_stdp, "prob_output_inh":prob_output_inh,
"prob_noise_poi_conn":prob_noise_poi_conn, "tau_pl":tau_pl,
"stdp_w_max":stdp_w_max, "stdp_w_min":stdp_w_min, "stdp_A_pl":stdp_A_pl,
"wei_noise_poi":wei_noise_poi, "del_noise_poi":del_noise_poi,
"thr_data_plus":thr_data_plus, "thr_data_minus":thr_data_minus
}
if save == True:
np.save("output_files/parameters1",parameter_dict)
np.save("output_files/parameters2",del_src_enc)
############################################################################
## Create populations for different layers
############################################################################
poi_layer = []
enc_layer = []
filt_layer_exc = []
out_layer_exc = []
out_layer_inh = []
out_spike_source = []
# Calculate spike times at the input using the rate information coming from features
spike_times = [[] for i in range(n_feature)]
for i in range(n_trials):
t_st = i * time_int_trials
t_end = t_st + time_int_trials
ind = i * n_feature
for j in range(n_feature):
times = PoissonTimes(t_st, t_end, poi_rate[ind+j],
np.random.randint(100), max_rate=max(poi_rate))
for t in times:
spike_times[j].append(t)
if randomness == True: # if True: calculate "spike_times" (randomly) new
# uf False: load previously saved "spike_times"
np.save('output_files/spike_times_train.npy', spike_times)
else:
spike_times = np.load('output_files/spike_times_train.npy')
# Calculate spike times at the output (as supervisory signal)
out_spike_times=[[] for i in range(n_cl)]
for i in range(n_trials):
t_st = i * time_int_trials
t_end = t_st + time_int_trials
ind = outputs[i]
times = PoissonTimes(t_st, t_end, max_fr_rate_output,
np.random.randint(100))
for t in times:
out_spike_times[int(ind)].append(t)
if randomness == True: # if True: calculate "out_spike_times" (randomly) new
# uf False: load previously saved "out_spike_times"
np.save('output_files/out_spike_times.npy', out_spike_times)
else:
out_spike_times = np.load('output_files/out_spike_times.npy')
# Spike source of input layer
spike_source=p.Population(n_feature,
p.SpikeSourceArray,
{'spike_times':spike_times},
label='spike_source')
# Spike source of output layer (Supervisory signal)
for i in range(n_cl):
out_spike_source.append(p.Population(1, p.SpikeSourceArray,
{'spike_times':[out_spike_times[i]]}, label='out_spike_source'))
# Encoding layer and Filtering Layer definitions
enc_layer = p.Population(n_feature * n_pop,
p.IF_curr_exp,
cell_params_lif,
label='enc_layer')
filt_layer = p.Population(n_feature * n_pop,
p.IF_curr_exp,
cell_params_lif,
label='filt_layer')
# Excitatory and Inhibitory population definitions at the output
for i in range(n_cl):
out_layer_exc.append(p.Population(n_pop,
p.IF_curr_exp,
cell_params_lif,
label='out_layer_exc{}'.format(i)))
out_layer_inh.append(p.Population(n_pop,
p.IF_curr_exp,
cell_params_lif,
label='out_layer_inh{}'.format(i)))
out_layer_exc[i].record()
# Noisy poisson population at the input
poisson_input = p.Population(n_pop * 2,
p.SpikeSourcePoisson,
{"rate":noise_poi_rate})
# Record Spikes
enc_layer.record()
filt_layer.record()
#enc_layer.initialize('v',p.RandomDistribution('uniform',[-51.,-69.]))
#filt_layer.initialize('v',p.RandomDistribution('uniform',[-51.,-69.]))
############################################################################
## Projections
############################################################################
## Connection List from Spike Source Array to Encoding Layer
conn_inp_enc=[]
for i in range(n_feature):
ind=i*n_pop
for j in range(n_pop):
conn_inp_enc.append([i,ind+j,wei_src_enc,del_src_enc[ind+j]])
if save == True:
np.save("output_files/conn_inp_enc",conn_inp_enc)
## Connection List for Filtering Layer Inhibitory
if randomness == True: # if True: calculate conn_filt_inh (randomly) new
# uf False: load previously saved conn_filt_inh
conn_filt_inh=[]
for i in range(n_feature):
rng1=i*n_pop
rng2=rng1+n_pop
inp=range(rng1,rng2)
outp=range(0,rng1)+range(rng2,n_feature*n_pop)
for ii in inp:
for jj in outp:
if prob_filt_inh>np.random.rand():
conn_filt_inh.append([ii,jj,wei_filt_inh,del_filt_inh])
if save == True:
np.save('output_files/conn_filt_inh.npy', conn_filt_inh)
else:
conn_filt_inh = np.load('output_files/conn_filt_inh.npy')
## STDP Connection List
if randomness == True: # if True: calculate conn_stdp_list (randomly) new
# uf False: load previously saved conn_stdp_list
conn_stdp_list=[[] for i in range(n_cl)]
for i in range(n_cl): # For each population at output layer
if use_old_weights == True:
cl_weights = np.load(
"output_files/stdp_weights{}.npy".format(i))
w = 0
for ii in range(n_pop * n_feature): # For each neuron in filtering layer
for jj in range(n_pop): # For each neuron in each population of output layer
if prob_stdp > np.random.rand(): # If the prob of connection is satiesfied
# Make the connection
if use_old_weights == True:
conn_stdp_list[i].append([ii,
jj,
cl_weights[w],
del_init_stdp])
w += 1
else:
conn_stdp_list[i].append([ii,
jj,
wei_init_stdp,
del_init_stdp])
if use_old_weights == False or save == True:
np.save('output_files/conn_stdp_list.npy', conn_stdp_list)
else:
conn_stdp_list = np.load('output_files/conn_stdp_list.npy')
## Output Layer Inhibitory Connection List
if randomness == True: # if True: calculate conn_stdp_list (randomly) new
# uf False: load previously saved conn_stdp_list
conn_output_inh = [[] for i in range(n_cl) for j in range(n_cl) if i!=j]
c = 0
for i in range(n_cl):
for j in range(n_cl):
if i != j:
for ii in range(n_pop):
for jj in range(n_pop):
if prob_output_inh > np.random.rand():
conn_output_inh[c].append([ii,
jj,
wei_cls_inh,
del_cls_inh])
c += 1
if save == True:
np.save("output_files/conn_output_inh.npy",conn_output_inh)
else:
conn_output_inh = np.load("output_files/conn_output_inh.npy")
## Spike Source to Encoding Layer
p.Projection(spike_source, enc_layer,
p.FromListConnector(conn_inp_enc))
## Encoding Layer to Filtering Layer
p.Projection(enc_layer, filt_layer,
p.OneToOneConnector(weights=wei_enc_filt,
delays=del_enc_filt))
## Filtering Layer Inhibitory
p.Projection(filt_layer, filt_layer,
p.FromListConnector(conn_filt_inh),
target="inhibitory")
## STDP Connection between Filtering Layer and Output Layer
timing_rule = p.SpikePairRule(tau_plus=tau_pl,
tau_minus=tau_min)
weight_rule = p.AdditiveWeightDependence(w_max=stdp_w_max,
w_min=stdp_w_min,
A_plus=stdp_A_pl,
A_minus=stdp_A_min)
stdp_model = p.STDPMechanism(timing_dependence=timing_rule,
weight_dependence=weight_rule)
# STDP connection
stdp_proj = []
for j in range(n_cl):
stdp_proj.append(
p.Projection(filt_layer,out_layer_exc[j],
p.FromListConnector(conn_stdp_list[j]),
synapse_dynamics = p.SynapseDynamics(slow=stdp_model)))
## Connection between Output Layer neurons
c = 0
for i in range(n_cl):
p.Projection(out_layer_exc[i], out_layer_inh[i],
p.OneToOneConnector(weights=wei_cls_exc,
delays=del_cls_exc))
iter_array=[j for j in range(n_cl) if j!=i]
for j in iter_array:
p.Projection(out_layer_exc[i], out_layer_exc[j],
p.FromListConnector(conn_output_inh[c]),
target="inhibitory")
c += 1
## Spike Source Array to Output
for i in range(n_cl):
p.Projection(out_spike_source[i],
out_layer_exc[i],
p.AllToAllConnector(weights=wei_source_outp,
delays=del_source_outp))
iter_array = [j for j in range(n_cl) if j != i]
for j in iter_array:
p.Projection(out_spike_source[i],
out_layer_exc[j],
p.AllToAllConnector(weights=wei_source_outp,
delays=del_source_outp),
target="inhibitory")
#for i in range(n_cl):
# p.Projection(out_spike_source[i], out_layer_exc[i], p.AllToAllConnector\
# (weights=wei_source_outp, delays=del_source_outp))
# p.Projection(out_spike_source[i], out_layer_exc[1-i], p.AllToAllConnector\
# (weights=wei_source_outp, delays=del_source_outp),target="inhibitory")
## Noisy poisson connection to encoding layer
if randomness == True: # if True: connect noise to network
# if False: don't use noise in network
p.Projection(poisson_input, enc_layer,
p.FixedProbabilityConnector(p_connect=prob_noise_poi_conn,
weights=wei_noise_poi,
delays=del_noise_poi))
############################################################################
## Simulation
############################################################################
p.run(SIM_TIME)
Enc_Spikes = enc_layer.getSpikes()
Filt_Exc_Spikes = filt_layer.getSpikes()
Out_Spikes = [[] for i in range(n_cl)]
for i in range(n_cl):
Out_Spikes[i] = out_layer_exc[i].getSpikes()
wei = []
for i in range(n_cl):
ww = stdp_proj[i].getWeights()
if save == True:
np.save("output_files/stdp_weights{}".format(i), ww)
wei.append(ww)
p.end()
############################################################################
## Plot
############################################################################
## Plot 1: Encoding Layer Raster Plot
if 0:
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron ID')
pylab.title('Encoding Layer Raster Plot')
pylab.hold(True)
pylab.plot([i[1] for i in Enc_Spikes], [i[0] for i in Enc_Spikes], ".b")
pylab.hold(False)
#pylab.axis([-10,c*SIM_TIME+100,-1,numInp+numOut+numInp+3])
pylab.show()
## Plot 2-1: Filtering Layer Raster Plot
if 0:
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron ID')
pylab.title('Filtering Layer Raster Plot')
pylab.plot([i[1] for i in Filt_Exc_Spikes],
[i[0] for i in Filt_Exc_Spikes], ".b")
#pylab.axis([-10,c*SIM_TIME+100,-1,numInp+numOut+numInp+3])
pylab.show()
## Plot 2-2: Filtering Layer Layer Raster Plot
if 0:
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron ID')
pylab.title('Filtering Layer Layer Raster Plot')
pylab.hold(True)
pylab.plot([i[1] for i in Filt_Exc_Spikes],
[i[0] for i in Filt_Exc_Spikes], ".b")
time_ind=[i*time_int_trials for i in range(len(outputs))]
for i in range(len(time_ind)):
pylab.plot([time_ind[i],time_ind[i]],[0,2000],"r")
pylab.hold(False)
#pylab.axis([-10,c*SIM_TIME+100,-1,numInp+numOut+numInp+3])
pylab.show()
## Plot 3-1: Output Layer Raster Plot
if 0:
pylab.figure()
pylab.xlabel('Time (ms)')
pylab.ylabel('Neuron')
pylab.title('Output Layer Raster Plot')
pylab.hold(True)
c=0
for array in Out_Spikes:
pylab.plot([i[1] for i in array], [i[0]+c for i in array], ".b")
c+=0.2
pylab.hold(False)
pylab.axis([-10,SIM_TIME+100,-1,n_pop+3])
pylab.show()
## Plot 4: STDP WEIGHTS
if 1:
pylab.figure()
pylab.xlabel('Weight ID')
pylab.ylabel('Weight Value')
pylab.title('STDP weights at the end')
#pylab.title('STDP weights at the end' + ' (trail_num=' + str(trial_num) + ')')
pylab.hold(True)
for i in range(n_cl):
pylab.plot(wei[i])
pylab.hold(False)
pylab.axis([-10,n_pop*n_feature*n_pop*0.5+10,-stdp_w_max,2*stdp_w_max])
str_legend=["To Cl {}".format(i+1) for i in range(n_cl)]
pylab.legend(str_legend)
#pylab.show()
fname = 'plots/weights_1.png'
while True:
if os.path.isfile(fname): # if file already exists
new_num = int(fname.split('.')[0].split('_')[1]) + 1
fname = fname.split('_')[0] + '_' +str(new_num) + '.png'
# if len(fname) == 19:
# new_num = int(fname.split('.')[0][-1]) + 1
# fname = fname.split('.')[0][:-1] + str(new_num) + '.png'
# elif len(fname) == 20:
# new_num = int(fname.split('.')[0][-2:]) + 1
# fname = fname.split('.')[0][:-2] + str(new_num) + '.png'
# else:
# new_num = int(fname.split('.')[0][-3:]) + 1
# fname = fname.split('.')[0][:-3] + str(new_num) + '.png'
else:
pylab.savefig(fname)
break
#pylab.figure()
#pylab.xlabel('Weight ID')
#pylab.ylabel('Weight Value')
#pylab.title('STDP weights at the end')
#pylab.hold(True)
#pylab.plot(wei[0], "b")
#pylab.plot(wei[1], "g")
#pylab.hold(False)
#pylab.axis([-10, n_pop * n_feature * n_pop * 0.5 + 10,
# -stdp_w_max, 2 * stdp_w_max])
#pylab.legend(['To Cl 1','To Cl 2'])
#pylab.show()
## Plot 5: Spike Source Spiking Times
if 0:
pylab.figure()
pylab.hold(True)
pylab.plot(out_spike_times[0],
[1 for i in range(len(out_spike_times[0]))],"x")
pylab.plot(out_spike_times[1],
[1.05 for i in range(len(out_spike_times[1]))],"x")
pylab.hold(False)
pylab.title("Spike Source Spiking Times")
pylab.axis([-100,SIM_TIME+100,-2,3])
pylab.show()
## Calculate spiking activity of each neuron to each class inputs
sum_filt=[[0 for i in range(n_feature*n_pop)] for j in range(n_cl)]
sum_filt=np.array(sum_filt)
for i in range(n_trials):
t_st = i * time_int_trials
t_end = t_st + time_int_trials
cl = outputs[i]
for n,t in Filt_Exc_Spikes:
if t >= t_st and t < t_end:
sum_filt[int(cl),int(n)] = sum_filt[int(cl), int(n)] + 1
a4=sum_filt[0]
b4=sum_filt[1]
thr=20
diff_vec=np.abs(a4 - b4)
diff_thr=[i if i>thr else 0. for i in diff_vec]
diff_ind=[i for i in range(len(diff_thr)) if diff_thr[i]!=0]
if save == True:
np.save("output_files/diff_ind_filt",diff_ind)
diff2 = a4 - b4
diff_thr2=[i if i > thr or i <- thr else 0. for i in diff2]
diff_ind2=[i for i in range(len(diff_thr2)) if diff_thr2[i] != 0]
if save == True:
np.save("output_files/diff_ind_filt2",diff_ind2)
np.save("output_files/diff_thr2",diff_thr2)
## Plot 6: Total Spiking Activity of Neurons at Decomposition Layer for Each Class
if 0:
a4=sum_filt[0]
b4=sum_filt[1]
pylab.figure()
pylab.hold(True)
pylab.plot(a4,"b")
pylab.plot(b4,"r")
pylab.xlabel('Neuron ID')
pylab.ylabel('Total Firing Rates Through Trials')
pylab.title("Total Spiking Activity of Neurons at Decomposition Layer ",
"for Each Class")
pylab.hold(False)
pylab.legend(["Activity to AN1","Activity to AN2"])
pylab.show()
def run_test(w_list, cell_para, spike_source_data):
#Du.set_trace()
pop_list = []
p.setup(timestep=1.0, min_delay=1.0, max_delay=3.0)
#input poisson layer
input_size = w_list[0].shape[0]
#print w_list[0].shape[0]
#print w_list[1].shape[0]
list = []
for j in range(input_size):
list.append(spike_source_data[j])
pop_in = p.Population(input_size, p.SpikeSourceArray,
{'spike_times': list})
pop_list.append(pop_in)
#for j in range(input_size):
#pop_in[j].spike_times = spike_source_data[j]
#pop_in = p.Population(input_size, p.SpikeSourceArray, {'spike_times' : []})
#for j in range(input_size):
#pop_in[j].spike_times = spike_source_data[j]
#pop_list.append(pop_in)
#count =0
#print w_list[0].shape[0]
for w in w_list:
input_size = w.shape[0]
#count = count+1
#print count
output_size = w.shape[1]
#pos_w = np.copy(w)
#pos_w[pos_w < 0] = 0
#neg_w = np.copy(w)
#neg_w[neg_w > 0] = 0
conn_list_exci = []
conn_list_inhi = []
#k_size=in_size-out_size+1
for x_ind in range(input_size):
for y_ind in range(output_size):
weights = w[x_ind][y_ind]
#for i in range(w.shape[1]):
if weights > 0:
conn_list_exci.append((x_ind, y_ind, weights, 1.))
elif weights < 0:
conn_list_inhi.append((x_ind, y_ind, weights, 1.))
#print output_size
pop_out = p.Population(output_size, p.IF_curr_exp, cell_para)
if len(conn_list_exci) > 0:
p.Projection(pop_in,
pop_out,
p.FromListConnector(conn_list_exci),
target='excitatory')
if len(conn_list_inhi) > 0:
p.Projection(pop_in,
pop_out,
p.FromListConnector(conn_list_inhi),
target='inhibitory')
#p.Projection(pop_in, pop_out, p.AllToAllConnector(weights = pos_w), target='excitatory')
#p.Projection(pop_in, pop_out, p.AllToAllConnector(weights = neg_w), target='inhibitory')
pop_list.append(pop_out)
pop_in = pop_out
pop_out.record()
run_time = np.ceil(np.max(spike_source_data)[0] / 1000.) * 1000
#print run_time
p.run(run_time)
spikes = pop_out.getSpikes(compatible_output=True)
return spikes
import pyNN.spiNNaker as p
import memory_for_parser as mem
import parse as parser
import get_text as sp
NUMBER_PEOPLE = 10
NUMBER_LOCS = 10
NUMBER_OBJS = 10
max_delay = 100.0
p.setup(timestep=1.0, min_delay = 1.0, max_delay = max_delay)
# parser.parse_no_run('spiNNaker', "daniel went to the bathroom. john went to the hallway. where is john?")
sent1 = sp.getSentence(parser.words, "Say your first assertion now")
sent2 = sp.getSentence(parser.words, "Say your second assertion now")
sent3 = sp.getSentence(parser.words, "Ask your question now")
parser.parse_no_run('spiNNaker', sent1+sent2+sent3)
[input_populations, state_populations, output_populations, projections] = mem.memory(NUMBER_PEOPLE, NUMBER_LOCS, NUMBER_OBJS)
cell_params_lif = {'cm' : 0.25, # nF
'i_offset' : 0.0,
'tau_m' : 20.0,
'tau_refrac': 2.0,
'tau_syn_E' : 5.0,
'tau_syn_I' : 5.0,
'v_reset' : -70.0,
def estimate_kb(cell_params_lif):
cell_para = copy.deepcopy(cell_params_lif)
random.seed(0)
p.setup(timestep=1.0, min_delay=1.0, max_delay=16.0)
run_s = 10.
runtime = 1000. * run_s
max_rate = 1000.
ee_connector = p.OneToOneConnector(weights=1.0, delays=2.0)
pop_list = []
pop_output = []
pop_source = []
x = np.arange(0., 1.01, 0.1)
count = 0
trail = 10
for i in x:
for j in range(trail): #trails for average
pop_output.append(p.Population(1, p.IF_curr_exp, cell_para))
poisson_spikes = mu.poisson_generator(i * max_rate, 0, runtime)
pop_source.append(
p.Population(1, p.SpikeSourceArray,
{'spike_times': poisson_spikes}))
p.Projection(pop_source[count],
pop_output[count],
ee_connector,
target='excitatory')
pop_output[count].record()
count += 1
count = 0
for i in x:
cell_para['i_offset'] = i
pop_list.append(p.Population(1, p.IF_curr_exp, cell_para))
pop_list[count].record()
count += 1
pop_list[count - 1].record_v()
p.run(runtime)
rate_I = np.zeros(count)
rate_P = np.zeros(count)
rate_P_max = np.zeros(count)
rate_P_min = np.ones(count) * 1000.
for i in range(count):
spikes = pop_list[i].getSpikes(compatible_output=True)
rate_I[i] = len(spikes) / run_s
for j in range(trail):
spikes = pop_output[i * trail +
j].getSpikes(compatible_output=True)
spike_num = len(spikes) / run_s
rate_P[i] += spike_num
if spike_num > rate_P_max[i]:
rate_P_max[i] = spike_num
if spike_num < rate_P_min[i]:
rate_P_min[i] = spike_num
rate_P[i] /= trail
'''
#plot_spikes(spikes, 'Current = 10. mA')
plt.plot(x, rate_I, label='current',)
plt.plot(x, rate_P, label='Poisson input')
plt.fill_between(x, rate_P_min, rate_P_max, facecolor = 'green', alpha=0.3)
'''
x0 = np.where(rate_P > 1.)[0][0]
x1 = 4
k = (rate_P[x1] - rate_P[x0]) / (x[x1] - x[x0])
'''
plt.plot(x, k*(x-x[x0])+rate_P[x0], label='linear')
plt.legend(loc='upper left', shadow=True)
plt.grid('on')
plt.show()
'''
p.end()
return k, x[x0], rate_P[x0]
(http://neuralensemble.org/trac/NeuroTools)
Authors : Catherine Wacongne < *****@*****.** >
Xavier Lagorce < *****@*****.** >
April 2013
"""
try:
import pyNN.spiNNaker as sim
except Exception:
import spynnaker8 as sim
from pyNN.utility.plotting import Figure, Panel
import matplotlib.pyplot as plt
# SpiNNaker setup
sim.setup(timestep=1.0, min_delay=1.0, max_delay=10.0)
# +-------------------------------------------------------------------+
# | General Parameters |
# +-------------------------------------------------------------------+
# Population parameters
model = sim.IF_curr_exp
cell_params = {
'cm': 0.25,
'i_offset': 0.0,
'tau_m': 20.0,
'tau_refrac': 2.0,
'tau_syn_E': 5.0,
'tau_syn_I': 5.0,
#!/usr/bin/env python
import IPython
import pyNN.spiNNaker as p
#import pyNN.neuron as p
from pylab import *
from pyNN.utility import init_logging
from pyNN.utility import get_script_args
from pyNN.errors import RecordingError
spin_control = p.setup(timestep=0.1, min_delay=0.1, max_delay=4.0)
#init_logging("logfile", debug=True)
ifcell = p.Population(10, p.IF_cond_exp, { 'i_offset' : 0.1, 'tau_refrac' : 3.0,
'v_thresh' : -51.0, 'tau_syn_E' : 2.0,
'tau_syn_I': 5.0, 'v_reset' : -70.0,
'e_rev_E' : 0., 'e_rev_I' : -80.}, label = "myFinalCell_PLOT")
spike_sourceE = p.Population(10, p.SpikeSourceArray, {'spike_times': [float(i) for i in range(0,9000,100)]}, label = "mySourceE_PLOT")
spike_sourceI = p.Population(10, p.SpikeSourceArray, {'spike_times': [float(i) for i in range(1000,5000,50)]}, label = "mySourceI_PLOT")
connE = p.Projection(spike_sourceE, ifcell, p.AllToAllConnector(weights=1.0, delays=0.2), target='excitatory')
connI = p.Projection(spike_sourceI, ifcell, p.AllToAllConnector(weights=3.0, delays=0.2), target='inhibitory')
#p1 = Population(100, IF_curr_alpha, structure=space.Grid2D())
#prepop = p.Population(100 ,p.SpikeSourceArray,{'spike_times':[[i for i in arange(10,duration,100)], [i for i in arange(50,duration,100)]]*(nn/2)})
#prj2_1 = Projection(p2, p1, method=AllToAllConnector(), target='excitatory')