def train_single(self, input_vector, target_vector):
""""
Forward Propagation
input: input_vector [784], target_vector [10]
H1: output_vector [100], weights_in_hidden[100, 784], output_hidden[100]
output: output_vector2 [10], weight_hidden_output[10, 100], output_network[10]
loss scalar 2.3
Backward Propagation
gradient [10], derived [10], tmp2 [10], hidden_errors [100,10], tmp5 [100,10]
"""
input_vector = np.array(input_vector, ndmin=2).T
target_vector = np.array(target_vector, ndmin=2).T
output_vector1 = np.dot(self.weights_in_hidden, input_vector)
output_hidden = Activation.leakyReLU(output_vector1)
output_vector2 = np.dot(self.weights_hidden_output, output_hidden)
output_network = Activation.leakyReLU(output_vector2)
loss = Cross_Entropy.calc(output_network, target_vector)
gradient = Cross_Entropy.derived_calc(output_network, target_vector)
# update the weights:
derived1 = Derivative.leakyReLU(gradient)
tmp2 = derived1 * (loss * gradient)
# calculate hidden errors:
hidden_errors = np.dot(self.weights_hidden_output.T, loss * derived1)
# update the weights:
tmp5 = hidden_errors * Derivative.leakyReLU(output_hidden)
self.weights_hidden_output += self.learning_rate * np.dot(
tmp2, output_hidden.T)
self.weights_in_hidden += self.learning_rate * np.dot(
tmp5, input_vector.T)
def run(self, input_vector):
# input_vector can be tuple, list or ndarray
input_vector = np.array(input_vector, ndmin=2).T
# 1st layer
output_vector = np.dot(self.weights_in_hidden, input_vector)
output_vector = Activation.leakyReLU(output_vector)
# 2nd layer
output_vector = np.dot(self.weights_hidden_output, output_vector)
output_vector = Activation.leakyReLU(output_vector)
return output_vector