-
Notifications
You must be signed in to change notification settings - Fork 1
/
firstNeuralNetwork.py
123 lines (97 loc) · 3.87 KB
/
firstNeuralNetwork.py
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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
'''
This fully-connected neural network was made using numpy and not Tensorflow.
This was a test of neural networks before I was better acquainted with them
and before tensorflow was released to the public.
'''
import numpy as np
from scipy import optimize
class Neural_Network(object):
def __init__(self):
#Define Hyperparameters
self.inputLayerSize = 1
self.outputLayerSize = 1
self.hiddenLayerSize = 3
#Weights (parameters)
self.W1 = np.random.randn(self.inputLayerSize,self.hiddenLayerSize)
self.W2 = np.random.randn(self.hiddenLayerSize,self.outputLayerSize)
def forward(self, X):
#Propogate inputs though network
self.z2 = np.dot(X, self.W1)
self.a2 = self.sigmoid(self.z2)
self.z3 = np.dot(self.a2, self.W2)
yHat = self.sigmoid(self.z3)
return yHat
def sigmoid(self, z):
#Apply sigmoid activation function to scalar, vector, or matrix
return 1/(1+np.exp(-z))
def sigmoidPrime(self,z):
#Gradient of sigmoid
return np.exp(-z)/((1+np.exp(-z))**2)
def costFunction(self, X, y):
#Compute cost for given X,y, use weights already stored in class.
self.yHat = self.forward(X)
J = 0.5*sum((y-self.yHat)**2)
return J
def costFunctionPrime(self, X, y):
#Compute derivative with respect to W and W2 for a given X and y:
self.yHat = self.forward(X)
delta3 = np.multiply(-(y-self.yHat), self.sigmoidPrime(self.z3))
dJdW2 = np.dot(self.a2.T, delta3)
delta2 = np.dot(delta3, self.W2.T)*self.sigmoidPrime(self.z2)
dJdW1 = np.dot(X.T, delta2)
return dJdW1, dJdW2
#Helper Functions for interacting with other classes:
def getParams(self):
#Get W1 and W2 unrolled into vector:
params = np.concatenate((self.W1.ravel(), self.W2.ravel()))
return params
def setParams(self, params):
#Set W1 and W2 using single paramater vector.
W1_start = 0
W1_end = self.hiddenLayerSize * self.inputLayerSize
self.W1 = np.reshape(params[W1_start:W1_end], (self.inputLayerSize , self.hiddenLayerSize))
W2_end = W1_end + self.hiddenLayerSize*self.outputLayerSize
self.W2 = np.reshape(params[W1_end:W2_end], (self.hiddenLayerSize, self.outputLayerSize))
def computeGradients(self, X, y):
dJdW1, dJdW2 = self.costFunctionPrime(X, y)
return np.concatenate((dJdW1.ravel(), dJdW2.ravel()))
class trainer(object):
def __init__(self, N):
#Make Local reference to network:
self.N = N
def callbackF(self, params):
self.N.setParams(params)
self.J.append(self.N.costFunction(self.X, self.y))
def costFunctionWrapper(self, params, X, y):
self.N.setParams(params)
cost = self.N.costFunction(X, y)
grad = self.N.computeGradients(X,y)
return cost, grad
def train(self, X, y):
#Make an internal variable for the callback function:
self.X = X
self.y = y
#Make empty list to store costs:
self.J = []
params0 = self.N.getParams()
options = {'maxiter': 200, 'disp' : True}
_res = optimize.minimize(self.costFunctionWrapper, params0, jac=True, method='BFGS', \
args=(X, y), options=options, callback=self.callbackF)
self.N.setParams(_res.x)
self.optimizationResults = _res
def generateX(num):
x = np.random.randint(100, size=num)
return x
def findY(x):
y = (x**(1/2))/10
return y
NN = Neural_Network()
TR = trainer(NN)
xT = np.vstack(generateX(70))
yT = (findY(xT))
TR.train(xT, yT)
x = np.vstack(generateX(3))
y = (findY(x))
print("x",x)
print("yHat",NN.forward(x))
print("y",y)