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 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 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 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 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
fast_injector.set("spike_times", [fast_spikes] + [[]] * 9)
if last_spike_slow < total_run_time + time_to_run:
slow_spikes = list(islice(slow_spike_iter, 10))
last_spike_slow = slow_spikes[-1]
slow_injector.set("spike_times", [slow_spikes] + [[]] * 9)
sim.run(time_to_run)
total_run_time += time_to_run
plt.xlim(max(0, total_run_time - 5*time_to_run), total_run_time)
if mode == "spikes":
plt.ylim(-1, 101)
all_spikes = populations[-1].getSpikes()
print "Total spikes %d" % len(all_spikes)
spikes = list(takewhile(lambda x: x[1] > total_run_time - time_to_run, all_spikes))
plt.plot([i[1] for i in spikes], [i[0] for i in spikes], ".", markersize=2)
else:
plt.ylim(v_reset - 5, v_thresh + 5)
voltages = list(ifilter(lambda x: x[0] == 1 and x[1] >= total_run_time - time_to_run,
reversed(populations[0].get_v())))
plt.plot([i[1] for i in voltages], [i[2] for i in voltages], "b-", markersize=1)
plt.draw()
plt.pause(0.001)
if not plt.get_fignums():
running = False
sim.end()
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]
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
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]
def end():
spynnaker.end()
def lancement_sim(cellSourceSpikes,
path,
weight_input=0,
weight_inter=0,
max_time=800000,
TIME_STEP=TIME_STEP,
input_n=input_n,
nb_neuron_int=nb_neuron_int,
nb_neuron_out=nb_neuron_out,
delay=delay,
p_conn_in_int=p_conn_in_int,
p_conn_int_out=p_conn_int_out,
v_tresh=v_tresh):
simulator = 'spinnaker'
# le max_delay doit être inférieur à 14*time_step
sim.setup(timestep=TIME_STEP, min_delay=delay, max_delay=delay * 2)
randoms = np.random.rand(100, 1)
#defining network topology
lif_curr_exp_params = {
'cm': 1.0, # The capacitance of the LIF neuron in nano-Farads
'tau_m': 20.0, # The time-constant of the RC circuit, in milliseconds
'tau_refrac': 5.0, # The refractory period, in milliseconds
'v_reset':
-65.0, # The voltage to set the neuron at immediately after a spike
'v_rest': -65.0, # The ambient rest voltage of the neuron
'v_thresh':
-(v_tresh), # The threshold voltage at which the neuron will spike
'tau_syn_E': 5.0, # The excitatory input current decay time-constant
'tau_syn_I': 5.0, # The inhibitory input current decay time-constant
'i_offset': 0.0, # A base input current to add each timestep
}
# Population d'entrée avec comme source le SpikeSourceArray en paramètre
Input = sim.Population(input_n,
sim.SpikeSourceArray(spike_times=cellSourceSpikes),
label="Input")
Input.record("spikes")
# Définition des types de neurones et des couches intermédiaire, de sortie, ainsi que celle contenant le neurone de l'attention
LIF_Intermediate = sim.IF_curr_exp(**lif_curr_exp_params)
Intermediate = sim.Population(nb_neuron_int,
LIF_Intermediate,
label="Intermediate")
Intermediate.record(("spikes", "v"))
LIF_Output = sim.IF_curr_exp(**lif_curr_exp_params)
Output = sim.Population(nb_neuron_out, LIF_Output, label="Output")
Output.record(("spikes", "v"))
LIF_delayer = sim.IF_curr_exp(**lif_curr_exp_params)
Delay_n = sim.Population(1, LIF_delayer, label="Delay")
Delay_n.record(("spikes", "v"))
# set the stdp mechanisim parameters, we are going to use stdp in both connections between (input-intermediate) adn (intermediate-output)
python_rng = NumpyRNG(seed=98497627)
delay = delay # (ms) synaptic time delay
#A_minus
# définition des connexions entre couches de neurones entrée <=> intermédiaire, intermédiaire <=> sortie
# vérificatio pour savoir si on est dans le cas de la première simulation par défault ou si on doit injecter les poids
if ((weight_input != 0) or (weight_inter != 0)):
# cas ou l'on inject les poids
Conn_input_inter = sim.Projection(
Input,
Intermediate,
# Le fromListConnector pour injecter les poids
connector=sim.FromListConnector(weight_input),
receptor_type="excitatory",
label="Connection input to intermediate",
# des synapses static pour "suprimer" l'apprentissage
synapse_type=sim.StaticSynapse())
Conn_inter_output = sim.Projection(
Intermediate,
Output, # pre and post population
connector=sim.FromListConnector(weight_inter),
receptor_type="excitatory",
label="Connection intermediate to output",
synapse_type=sim.StaticSynapse())
else:
# cas par défault
Conn_input_inter = sim.Projection(
Input,
Intermediate,
connector=sim.FixedProbabilityConnector(
p_conn_in_int, allow_self_connections=False),
synapse_type=sim.StaticSynapse(
weight=RandomDistribution('normal', (3, 2.9), rng=python_rng)),
receptor_type="excitatory",
label="Connection input to intermediate")
Conn_inter_output = sim.Projection(
Intermediate,
Output, # pre and post population
connector=sim.FixedProbabilityConnector(
p_conn_int_out, allow_self_connections=False),
synapse_type=sim.StaticSynapse(
weight=RandomDistribution('normal', (3, 2.9), rng=python_rng)),
receptor_type="excitatory",
label="Connection intermediate to output")
# définition des connexions inhibitrices des couches intermédiaire et de sortie
FixedInhibitory_WTA = sim.StaticSynapse(weight=6)
WTA_INT = sim.Projection(
Intermediate,
Intermediate,
connector=sim.AllToAllConnector(allow_self_connections=False),
synapse_type=FixedInhibitory_WTA,
receptor_type="inhibitory",
label="Connection WTA")
WTA_OUT = sim.Projection(
Output,
Output,
connector=sim.AllToAllConnector(allow_self_connections=False),
synapse_type=FixedInhibitory_WTA,
receptor_type="inhibitory",
label="Connection WTA")
# Connexion avec le neurone de l'attention
FixedInhibitory_delayer = sim.StaticSynapse(weight=2)
Delay_out = sim.Projection(
Delay_n,
Output,
connector=sim.AllToAllConnector(allow_self_connections=False),
synapse_type=FixedInhibitory_delayer,
receptor_type="inhibitory",
label="Connection WTA")
Delay_inter = sim.Projection(
Intermediate,
Delay_n,
connector=sim.AllToAllConnector(allow_self_connections=False),
synapse_type=FixedInhibitory_delayer,
receptor_type="inhibitory",
label="Connection WTA")
# On précise le nombre de neurone par coeurs au cas ou
sim.set_number_of_neurons_per_core(sim.IF_curr_exp, 255)
# on arrondie le temps de simulation, sinon avec les callbacks, on a une boucle infinie pour des temps d'arrêts plus précis que la fréquence des callbacks
simtime = ceil(max_time)
try:
#lancement de la simulation
sim.run(simtime)
#récupération des infos sur les spike des trois couches
neo = Output.get_data(variables=["spikes", "v"])
spikes = neo.segments[0].spiketrains
#print(spikes)
v = neo.segments[0].filter(name='v')[0]
neo_in = Input.get_data(variables=["spikes"])
spikes_in = neo_in.segments[0].spiketrains
#print(spikes_in)
neo_intermediate = Intermediate.get_data(variables=["spikes", "v"])
spikes_intermediate = neo_intermediate.segments[0].spiketrains
#print(spikes_intermediate)
v_intermediate = neo_intermediate.segments[0].filter(name='v')[0]
#print(v_intermediate)
sim.reset()
sim.end()
except:
# Si la simulation fail, on set ces deux variables à zéros pour gérer l'erreur dans le script principal
v = 0
spikes = 0
# Création et sauvegarde des graphs des graphs si la simluation s'est bien passée, + envoie des sorties de la fonction
if (isinstance(spikes, list) and isinstance(v, AnalogSignal)):
plot.Figure(
# plot voltage for first ([0]) neuron
plot.Panel(v,
ylabel="Membrane potential (mV)",
data_labels=[Output.label],
yticks=True,
xlim=(0, simtime)),
# plot spikes (or in this case spike)
plot.Panel(spikes, yticks=True, markersize=5, xlim=(0, simtime)),
title="Spiking activity of the output layer during test",
annotations="Simulated with {}".format(sim.name())).save(
"./Generated_data/tests/" + path +
"/output_layer_membrane_voltage_and_spikes.png")
plot.Figure(
# plot voltage for first ([0]) neuron
plot.Panel(v_intermediate,
ylabel="Membrane potential (mV)",
data_labels=[Output.label],
yticks=True,
xlim=(0, simtime)),
# plot spikes (or in this case spike)
plot.Panel(spikes_intermediate,
yticks=True,
markersize=5,
xlim=(0, simtime)),
title="Spiking activity of the intermediate layer during test",
annotations="Simulated with {}".format(sim.name())).save(
"./Generated_data/tests/" + path +
"/intermediate_layer_membrane_voltage_and_spikes.png")
return v, spikes
else:
print(
"simulation failed with parameters : (l'affichage des paramètres ayant causés le disfonctionnement de la simulation sera traitée à une date ultérieur, merci!)"
)
return 0, 0
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
print(spikesum)
print('estimate = ' + str(np.argmax(spikesum)))
except:
print("COULD NOT RUN TRIAL " + str(trial))
pred_labels.append(np.zeros(5))
#get spikes for plotting
spiketrains_all.append(spiketrains_flat)
#end simulation
pynn.end()
print('simulation end')
s = []
a = []
i = 0
for spiketrain in spiketrains_all:
eventdata = []
for dat in spiketrain:
eventdata.append(np.nonzero(dat)[0])
plt.figure()
plt.eventplot(eventdata)
def end():
spynnaker.end()
pylab.title('spikes')
pylab.show()
else:
print "No spikes received"
# Make some graphs
if v is not None:
ticks = len(v) / nNeurons
pylab.figure()
pylab.xlabel('Time/ms')
pylab.ylabel('v')
pylab.title('v')
for pos in range(0, nNeurons, 20):
v_for_neuron = v[pos * ticks: (pos + 1) * ticks]
pylab.plot([i[2] for i in v_for_neuron])
pylab.show()
if gsyn is not None:
ticks = len(gsyn) / nNeurons
pylab.figure()
pylab.xlabel('Time/ms')
pylab.ylabel('gsyn')
pylab.title('gsyn')
for pos in range(0, nNeurons, 20):
gsyn_for_neuron = gsyn[pos * ticks: (pos + 1) * ticks]
pylab.plot([i[2] for i in gsyn_for_neuron])
pylab.show()
p.end()
n = n % len(seq)
return seq[n:] + seq[:n]
# connect all populations, but don't close the chain
for pop_a, pop_b in zip(all_pops, shift(all_pops, 1)[:-1]):
pynn.Projection(pop_a, pop_b, con_fixednumberpre, target='excitatory')
pynn.run(duration)
spikes = None
# Collect and record spikes
for pop in all_pops:
new_spikes = pop.getSpikes(compatible_output=True)
if new_spikes is not None:
numpy.fliplr(new_spikes)
new_spikes = new_spikes / [1, 1000.0]
if spikes is None:
spikes = new_spikes
else:
new_spikes = new_spikes + [len(spikes), 0]
spikes = numpy.concatenate((spikes, new_spikes), axis=0)
if spikes is None:
spikes = []
print "N spikes", len(spikes)
numpy.savetxt("spikes.dat", spikes)
pynn.end()
pylab.title('spikes')
pylab.show()
else:
print "No spikes received"
# Make some graphs
if v is not None:
ticks = len(v) / nNeurons
pylab.figure()
pylab.xlabel('Time/ms')
pylab.ylabel('v')
pylab.title('v')
for pos in range(0, nNeurons, 20):
v_for_neuron = v[pos * ticks: (pos + 1) * ticks]
pylab.plot([i[2] for i in v_for_neuron])
pylab.show()
if gsyn is not None:
ticks = len(gsyn) / nNeurons
pylab.figure()
pylab.xlabel('Time/ms')
pylab.ylabel('gsyn')
pylab.title('gsyn')
for pos in range(0, nNeurons, 20):
gsyn_for_neuron = gsyn[pos * ticks: (pos + 1) * ticks]
pylab.plot([i[2] for i in gsyn_for_neuron])
pylab.show()
p.end()
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()
# +-------------------------------------------------------------------+
# Record neurons' potentials
pre_pop.record(['v', 'spikes'])
post_pop.record(['v', 'spikes'])
# Run simulation
sim.run(simtime)
print("Weights:{}".format(plastic_projection.get('weight', 'list')))
pre_spikes = pre_pop.get_data('spikes')
post_spikes = post_pop.get_data('spikes')
Figure(
# raster plot of the presynaptic neuron spike times
Panel(pre_spikes.segments[0].spiketrains,
yticks=True,
markersize=0.2,
xlim=(0, simtime)),
Panel(post_spikes.segments[0].spiketrains,
yticks=True,
markersize=0.2,
xlim=(0, simtime)),
title="stdp example curr",
annotations="Simulated with {}".format(sim.name()))
plt.show()
# End simulation on SpiNNaker
sim.end()
def lancement_sim(cellSourceSpikes,
max_time=800000,
path="default",
TIME_STEP=TIME_STEP,
input_n=input_n,
nb_neuron_int=nb_neuron_int,
nb_neuron_out=nb_neuron_out,
delay=delay,
p_conn_in_int=p_conn_in_int,
p_conn_int_out=p_conn_int_out,
a_minus=0.6,
a_plus=0.6,
tau_minus=12.0,
tau_plus=10.0,
v_tresh=10.0):
simulator = 'spinnaker'
sim.setup(timestep=TIME_STEP, min_delay=delay, max_delay=delay * 2)
randoms = np.random.rand(100, 1)
lif_curr_exp_params = {
'cm': 1.0, # The capacitance of the LIF neuron in nano-Farads
'tau_m': 20.0, # The time-constant of the RC circuit, in milliseconds
'tau_refrac': 5.0, # The refractory period, in milliseconds
'v_reset':
-65.0, # The voltage to set the neuron at immediately after a spike
'v_rest': -65.0, # The ambient rest voltage of the neuron
'v_thresh':
-(v_tresh), # The threshold voltage at which the neuron will spike
'tau_syn_E': 5.0, # The excitatory input current decay time-constant
'tau_syn_I': 5.0, # The inhibitory input current decay time-constant
'i_offset': 0.0, # A base input current to add each timestep
}
Input = sim.Population(input_n,
sim.SpikeSourceArray(spike_times=cellSourceSpikes),
label="Input")
Input.record("spikes")
LIF_Intermediate = sim.IF_curr_exp(**lif_curr_exp_params)
Intermediate = sim.Population(nb_neuron_int,
LIF_Intermediate,
label="Intermediate")
Intermediate.record(("spikes", "v"))
LIF_Output = sim.IF_curr_exp(**lif_curr_exp_params)
Output = sim.Population(nb_neuron_out, LIF_Output, label="Output")
Output.record(("spikes", "v"))
LIF_delayer = sim.IF_curr_exp(**lif_curr_exp_params)
Delay_n = sim.Population(1, LIF_delayer, label="Delay")
Delay_n.record(("spikes", "v"))
python_rng = NumpyRNG(seed=98497627)
delay = delay # (ms) synaptic time delay
# Définition du fonctionnement de la stdp
stdp_proj = sim.STDPMechanism(
timing_dependence=sim.SpikePairRule(tau_plus=tau_plus,
tau_minus=tau_minus,
A_plus=a_plus,
A_minus=a_minus),
weight_dependence=sim.AdditiveWeightDependence(w_min=0.1, w_max=6),
weight=RandomDistribution('normal', (3, 2.9), rng=python_rng),
delay=delay)
Conn_input_inter = sim.Projection(
Input,
Intermediate,
connector=sim.FixedProbabilityConnector(p_conn_in_int,
allow_self_connections=False),
# synapse type set avec la définition de la stdp pour l'aprentsissage
synapse_type=stdp_proj,
receptor_type="excitatory",
label="Connection input to intermediate")
# second projection with stdp
Conn_inter_output = sim.Projection(
Intermediate,
Output, # pre and post population
connector=sim.FixedProbabilityConnector(p_conn_int_out,
allow_self_connections=False),
synapse_type=stdp_proj,
receptor_type="excitatory",
label="Connection intermediate to output")
FixedInhibitory_WTA = sim.StaticSynapse(weight=6)
WTA_INT = sim.Projection(
Intermediate,
Intermediate,
connector=sim.AllToAllConnector(allow_self_connections=False),
synapse_type=FixedInhibitory_WTA,
receptor_type="inhibitory",
label="Connection WTA")
WTA_OUT = sim.Projection(
Output,
Output,
connector=sim.AllToAllConnector(allow_self_connections=False),
synapse_type=FixedInhibitory_WTA,
receptor_type="inhibitory",
label="Connection WTA")
FixedInhibitory_delayer = sim.StaticSynapse(weight=2)
Delay_out = sim.Projection(
Delay_n,
Output,
connector=sim.AllToAllConnector(allow_self_connections=False),
synapse_type=FixedInhibitory_delayer,
receptor_type="inhibitory",
label="Connection WTA")
Delay_inter = sim.Projection(
Intermediate,
Delay_n,
connector=sim.AllToAllConnector(allow_self_connections=False),
synapse_type=FixedInhibitory_delayer,
receptor_type="inhibitory",
label="Connection WTA")
sim.set_number_of_neurons_per_core(sim.IF_curr_exp, 255)
# Définition des callbacks pour la récupération de l'écart-type sur les connexions entrée-intermédiaire, intermédiaire-sortie
weight_recorder1 = WeightRecorder(sampling_interval=1000.0,
projection=Conn_input_inter)
weight_recorder2 = WeightRecorder(sampling_interval=1000.0,
projection=Conn_inter_output)
simtime = ceil(max_time)
# Initialisation des tableaux pour la récupération des poids
weights_int = []
weights_out = []
try:
sim.run(simtime, callbacks=[weight_recorder1, weight_recorder2])
neo = Output.get_data(variables=["spikes", "v"])
spikes = neo.segments[0].spiketrains
#print(spikes)
v = neo.segments[0].filter(name='v')[0]
weights_int = Conn_input_inter.get(["weight"], format="list")
neo_in = Input.get_data(variables=["spikes"])
spikes_in = neo_in.segments[0].spiketrains
#print(spikes_in)
neo_intermediate = Intermediate.get_data(variables=["spikes", "v"])
spikes_intermediate = neo_intermediate.segments[0].spiketrains
#print(spikes_intermediate)
v_intermediate = neo_intermediate.segments[0].filter(name='v')[0]
#print(v_intermediate)
weights_out = Conn_inter_output.get(["weight"], format="list")
sim.reset()
sim.end()
except:
v = 0
spikes = 0
if (isinstance(spikes, list) and isinstance(v, AnalogSignal)):
# Récupération des écart-types
standard_deviation_out = weight_recorder2.get_standard_deviations()
standard_deviation_int = weight_recorder1.get_standard_deviations()
t = np.arange(0., max_time, 1.)
# Création et sauvegarde des graphs sur les spikes et écart-types
savePath = "./Generated_data/training/" + path + "/intermediate_layer_standard_deviation.png"
plt.plot(standard_deviation_int)
plt.xlabel("callbacks tick (1s)")
plt.ylabel("standard deviation of the weights( wmax=6, wmin=0.1 )")
plt.savefig(savePath)
plt.clf()
savePath = "./Generated_data/training/" + path + "/output_layer_standard_deviation.png"
plt.plot(standard_deviation_out)
plt.xlabel("callbacks tick")
plt.ylabel("standard deviation ( wmax=6, wmin=0.1 )")
plt.savefig(savePath)
plt.clf()
savePath = "./Generated_data/training/" + path + "/output_layer_membrane_voltage_and_spikes.png"
plot.Figure(
# plot voltage for first ([0]) neuron
plot.Panel(v,
ylabel="Membrane potential (mV)",
data_labels=[Output.label],
yticks=True,
xlim=(0, simtime)),
# plot spikes (or in this case spike)
plot.Panel(spikes, yticks=True, markersize=5, xlim=(0, simtime)),
title="Spiking activity of the output layer during training",
annotations="Simulated with {}".format(sim.name())).save(savePath)
savePath = "./Generated_data/training/" + path + "/intermediate_layer_membrane_voltage_and_spikes.png"
plot.Figure(
# plot voltage for first ([0]) neuron
plot.Panel(v_intermediate,
ylabel="Membrane potential (mV)",
data_labels=[Output.label],
yticks=True,
xlim=(0, simtime)),
# plot spikes (or in this case spike)
plot.Panel(spikes_intermediate,
yticks=True,
markersize=5,
xlim=(0, simtime)),
title="Spiking activity of the intermediate layer during training",
annotations="Simulated with {}".format(sim.name())).save(savePath)
return v, spikes, weights_int, weights_out
else:
print(
"simulation failed with parmaters parameters : (l'affichage des paramètres ayant causés le disfonctionnement de la simulation sera traitée à une date ultérieur, merci!)"
)
return 0, 0, 0, 0