miloharper

import math
import random
import pickle
import os

class NeuralNetwork():
	def __init__(self):

		# Seed the random number generator, so we get the same random numbers each time
		random.seed(1)

miloharper

# We train the neural network through a process of trial and error.
# Adjusting the synaptic weights each time.
def train(self, training_set_inputs, training_set_outputs, number_of_training_iterations):
    for iteration in xrange(number_of_training_iterations):
        # Pass the training set through our neural network
        output_from_layer_1, output_from_layer_2 = self.think(training_set_inputs)

        # Calculate the error for layer 2 (The difference between the desired output
        # and the predicted output).
        layer2_error = training_set_outputs - output_from_layer_2

miloharper

def train(self, example):
    self.reset_errors()
    error = example.output - self.think(example.inputs)
    self.layers[-1].neurons[0].error = error
    for l in range(len(self.layers) - 1, 0, -1):
        for neuron in self.layers[l].neurons:
            self.layers[l - 1] = neuron.train(self.layers[l - 1])

miloharper

def train(self, previous_layer):
    for synapse in self.synapses:
        # Propagate the error back down the synapse to the neuron in the layer below
        previous_layer.neurons[synapse.input_neuron_index].error += self.error * sigmoid_derivative(self.output) * synapse.weight
        # Adjust the synapse weight
        synapse.weight += synapse.signal * self.error * sigmoid_derivative(self.output)
    return previous_layer

miloharper

from neural_network import NeuralNetwork
from formulae import calculate_average_error
from video import generate_writer, new_frame, annotate_frame, take_still
import parameters


class TrainingExample():
    def __init__(self, inputs, output):
        self.inputs = inputs
        self.output = output

miloharper

Stage 1) Random starting synaptic weights: 
    Layer 1 (4 neurons, each with 3 inputs): 
[[-0.16595599  0.44064899 -0.99977125 -0.39533485]
 [-0.70648822 -0.81532281 -0.62747958 -0.30887855]
 [-0.20646505  0.07763347 -0.16161097  0.370439  ]]
    Layer 2 (1 neuron, with 4 inputs):
[[-0.5910955 ]
 [ 0.75623487]
 [-0.94522481]
 [ 0.34093502]]

miloharper

from numpy import exp, array, random, dot


class NeuronLayer():
    def __init__(self, number_of_neurons, number_of_inputs_per_neuron):
        self.synaptic_weights = 2 * random.random((number_of_inputs_per_neuron, number_of_neurons)) - 1


class NeuralNetwork():
    def __init__(self, layer1, layer2):

miloharper

from numpy import exp, array, random, dot
training_set_inputs = array([[0, 0, 1], [1, 1, 1], [1, 0, 1], [0, 1, 1]])
training_set_outputs = array([[0, 1, 1, 0]]).T
random.seed(1)
synaptic_weights = 2 * random.random((3, 1)) - 1
for iteration in xrange(10000):
    output = 1 / (1 + exp(-(dot(training_set_inputs, synaptic_weights))))
    synaptic_weights += dot(training_set_inputs.T, (training_set_outputs - output) * output * (1 - output))
print 1 / (1 + exp(-(dot(array([1, 0, 0]), synaptic_weights))))

miloharper

training_set_inputs = array([[0, 0, 1], [1, 1, 1], [1, 0, 1], [0, 1, 1]])
training_set_outputs = array([[0, 1, 1, 0]]).T

miloharper

from numpy import exp, array, random, dot


class NeuralNetwork():
    def __init__(self):
        # Seed the random number generator, so it generates the same numbers
        # every time the program runs.
        random.seed(1)

        # We model a single neuron, with 3 input connections and 1 output connection.