1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96

import numpy as np
# X = (hours studying, hours sleeping), y = score on test, xPredicted = 4 hours studying & 8 hours sleeping (input data for prediction)
X = np.array(([2, 9], [1, 5], [3, 6]), dtype=float)
y = np.array(([92], [100], [89]), dtype=float)

xPredicted = np.array(([4, 8]), dtype=float)

# scale units
X = X / np.amax(X, axis=0)  # maximum of X array
xPredicted = xPredicted / np.amax(
    xPredicted,
    axis=0)  # maximum of xPredicted (our input data for the prediction)
y = y / 100  # max test score is 100


class Neural_Network(object):
    def __init__(self):
        #parameters
        self.inputSize = 2
        self.outputSize = 1
        self.hiddenSize = 3

        #weights
        self.W1 = np.random.randn(
            self.inputSize,
            self.hiddenSize)  # (3x2) weight matrix from input to hidden layer
        self.W2 = np.random.randn(
            self.hiddenSize,
            self.outputSize)  # (3x1) weight matrix from hidden to output layer

    def forward(self, X):
        #forward propagation through our network
        self.z = np.dot(
            X,
            self.W1)  # dot product of X (input) and first set of 3x2 weights
        self.z2 = self.sigmoid(self.z)  # activation function
        self.z3 = np.dot(
            self.z2, self.W2
        )  # dot product of hidden layer (z2) and second set of 3x1 weights
        o = self.sigmoid(self.z3)  # final activation function
        return o

    def sigmoid(self, s):
        # activation function
        return 1 / (1 + np.exp(-s))

    def sigmoidPrime(self, s):
        #derivative of sigmoid
        return s * (1 - s)

    def backward(self, X, y, o):
        # backward propgate through the network
        self.o_error = y - o  # error in output
        self.o_delta = self.o_error * self.sigmoidPrime(
            o)  # applying derivative of sigmoid to error

        self.z2_error = self.o_delta.dot(
            self.W2.T
        )  # z2 error: how much our hidden layer weights contributed to output error
        self.z2_delta = self.z2_error * self.sigmoidPrime(
            self.z2)  # applying derivative of sigmoid to z2 error

        self.W1 += X.T.dot(
            self.z2_delta)  # adjusting first set (input --> hidden) weights
        self.W2 += self.z2.T.dot(
            self.o_delta)  # adjusting second set (hidden --> output) weights

    def train(self, X, y):
        o = self.forward(X)
        self.backward(X, y, o)

    def saveWeights(self):
        np.savetxt("w1.txt", self.W1, fmt="%s")
        np.savetxt("w2.txt", self.W2, fmt="%s")

    def predict(self):
        print "Predicted data based on trained weights: "
        print "Input (scaled): \n" + str(xPredicted)
        print "Output: \n" + str(self.forward(xPredicted))


NN = Neural_Network()
for i in xrange(5000):  # trains the NN 1,000 times
    print " #" + str(i) + "\n"
    print "Input (scaled): \n" + str(X)
    print "Actual Output: \n" + str(y)
    print "Predicted Output: \n" + str(NN.forward(X))
    print "Loss: \n" + str(np.mean(
        np.square(y - NN.forward(X))))  # mean sum squared loss
    print "\n"
    NN.train(X, y)

NN.saveWeights()
NN.predict()

# full tutorial: https://enlight.nyc/neural-network