def __init__(self, sdr_size=1000):
super(CortexLocationAware, self).__init__(sdr_size=sdr_size)
self.receptive_field_pixels = (28, 28)
self.V1 = Area()
self.V1.add_layer(Layer('L4', shape=sdr_size))
self.V1.add_layer(
LocationAwareLayer('L23',
canvas_shape=(50, 50),
patch_shape=(20, 20)))
self.location_encoder = LocationEncoder(
max_amplitude=np.linalg.norm(IMAGE_SIZE), shape=sdr_size)
self.label_layer = LabelLayer(name="label", shape=sdr_size)
self.retina = Layer('retina', shape=self.receptive_field_pixels)
self.V1.layers['L4'].connect_input(self.retina)
self.V1.layers['L23'].connect_input(self.V1.layers['L4'])
def __init__(self, sdr_size=1000):
self.receptive_field_pixels = (28, 28)
self.V1 = Area()
self.display = False
self.V1.add_layer(Layer('L4', shape=sdr_size))
self.V1.add_layer(Layer('L23', shape=sdr_size))
self.V1.add_layer(Layer('motor_direction', shape=sdr_size))
self.V1.add_layer(Layer('motor_amplitude', shape=sdr_size))
self.location_encoder = LocationEncoder(
max_amplitude=np.linalg.norm(IMAGE_SIZE), shape=sdr_size)
self.label_layer = LabelLayer(name="label", shape=sdr_size)
self.retina = Layer('retina', shape=self.receptive_field_pixels)
self.V1.layers['L4'].connect_input(self.retina)
self.V1.layers['L23'].connect_input(self.V1.layers['motor_direction'])
self.V1.layers['L23'].connect_input(self.V1.layers['motor_amplitude'])
self.V1.layers['L23'].connect_input(self.V1.layers['L4'])
from random import uniform
from time import time
from core.layer import Layer, InputLayer, OutputLayer
from core.network import Network
with open('snek-learning.yaml', 'r') as file:
data = yaml.load(file)
#data = data[:1000]
learning_data = [{'inputs': list(row[:5]), 'outputs': [row[5]]} for row in data]
inputs = InputLayer([1, 1, 1, 1, 1])
middle = Layer(5)
middle3 = Layer(3)
output = OutputLayer([1])
network = Network([inputs, middle, middle3, output], 'snek')
network.connect()
network.load_learning_data(learning_data)
network.print_data()
folds = 4
result = [0]
i = 0
start_time = time()
while sum(result) / folds < 90:
results = network.learn_kfolds(folds, times=1)
scores = [(n, [round(x) for x in out] == check) for n, out, check in results]
'Iris-versicolor': [0, 1, 0],
'Iris-virginica': [1, 0, 0]
}
learning_data = []
with open('../data/training_data/iris.data', newline='') as csvfile:
reader = csv.reader(csvfile)
for row in reader:
learning_data.append({
'inputs': [float(x) for x in row[0:4]],
'outputs': iris_map[row[4]]
})
inputs = InputLayer([1, 1, 1, 1])
middle = Layer(5)
middle2 = Layer(3)
output = OutputLayer([1, 1, 1])
network = Network([inputs, middle, middle2, output], 'iris')
network.connect()
network.load_learning_data(learning_data)
network.normalize_learning_data()
print("------- learn -------")
network.print_data()
folds = 4
results = network.learn_kfolds(folds, times=1000)
scores = [(n, [round(x) for x in out] == check) for n, out, check in results]
stuff = Counter(scores)
def __init__(self, z_order):
Layer.__init__(self, z_order)
learning_data = []
with open('../data/training_data/iris.data', newline='') as csvfile:
reader = csv.reader(csvfile)
for row in reader:
learning_data.append({
'inputs': [float(x) for x in row[0:4]],
'outputs': iris_map[row[4]]
})
map = load_som("../data/trained_networks/som.yaml")
inputs = InputLayer([1, 1, 1, 1], name='NormalInput')
inputs_som = InputSom([1, 1, 1, 1], map)
inputs_som.set_network_name('som')
middle = Layer(3)
output = OutputLayer([1, 1, 1])
network = Network([inputs, middle, output], 'som')
network.connect()
network.load_learning_data(learning_data)
middle.connect_layer(inputs_som, 'left')
network.dump_cypher('../data/cypher/som.cypher',
additional_neurons=inputs_som.neurons)
"""
#network.learn(times=5000) #input_layers=[inputs_som])
folds = 4
results = network.learn_kfolds(folds, times=1000)
scores = [(n, [round(x) for x in out] == check) for n, out, check in results]
stuff = Counter(scores)
print("folds results: ", [stuff[(i, True)] / (stuff[(i,False)] + stuff[(i, True)]) * 100 for i in range(folds)])
from core.neuron import BiasNeuron
from core.layer import Layer, InputLayer, OutputLayer
from core.network import Network
net_name = 'xor'
inputs = InputLayer([1, 1])
middle = Layer(2)
middle2 = Layer(2)
output = OutputLayer([1])
network = Network([inputs, middle, middle2, output], net_name)
network.connect()
learning_data = [
{"inputs": [0, 0], "outputs": [0]},
{"inputs": [0, 1], "outputs": [1]},
{"inputs": [1, 1], "outputs": [0]},
{"inputs": [1, 0], "outputs": [1]}
]
network.load_learning_data(learning_data)
network.normalize_learning_data()
print("------- learn -------")
network.print_data()
network.learn(times=10000)
i = [[0, 0], [0, 1], [1, 1], [1, 0]]
def __init__(self, z_order):
Layer.__init__(self, z_order)
self.ground_type = GroundType.SAND
self.item = None
from core.layer import Layer, InputLayer, OutputLayer
from core.network import Network
inputs = InputLayer([1, 1, 1])
middle1 = Layer(4)
middle2 = Layer(3)
output = OutputLayer([1, 1])
network = Network([inputs, middle1, middle2, output])
network.connect()
#print("changing weight of {} to 0.3".format(middle1.neurons[0]))
#middle1.neurons[0].outputs[0].update_weight(0.3)
for _ in range(100):
print("-----middle1-------")
[print(x.inputs) for x in middle1.neurons]
[print(x.outputs) for x in middle1.neurons]
print("-----middle2-------")
[print(x.inputs) for x in middle2.neurons]
[print(x.outputs) for x in middle2.neurons]
network.stimulate()
network.backpropagate()
print("-----middle1-------")
[print(x.inputs) for x in middle1.neurons]
[print(x.outputs) for x in middle1.neurons]
print("-----middle2-------")
[print(x.inputs) for x in middle2.neurons]
def __init__(self, z_order):
Layer.__init__(self, z_order)
self.move_time = time.monotonic()
from core.network import Network
learning_data = []
tic_tac_map = {'positive': 1, 'negative': 0, 'x': 1, 'o': 2, 'b': 3}
with open('data/training_data/tic-tac-toe.data', newline='') as csvfile:
reader = csv.reader(csvfile)
for row in reader:
learning_data.append({
'inputs': [tic_tac_map[x] for x in row[0:9]],
'outputs': [tic_tac_map[row[9]]]
})
inputs = InputLayer([1] * 9)
middle = Layer(5)
middle2 = Layer(7)
middle3 = Layer(5)
middle4 = Layer(2)
output = OutputLayer([1])
network = Network([inputs, middle, middle2, middle3, middle4, output])
network.connect()
network.load_learning_data(learning_data)
#network.normalize_learning_data()
print("------- learn -------")
network.print_data()
#network.learn(times=100)
