I have been trying to implement a neural network in python that uses back propagation and keep getting the above error. How can I go about eliminating it. The code runs for one epoch without calculating the error in the system hence it is not able to back propagate the error across the network
import numpy as np
X = [0.4, 0.7]
y = [0.1]
class Neural_Network(object):
def __init__(self):
#parameters
self.inputSize = 2
self.outputSize = 1
self.hiddenSize = 2
#weights
self.W1 = [[0.1, 0.4],
[0.2, -0.2]] # (2x2) weight matrix from input to hidden layer
self.W2 = np.array([0.2, -0.5])[np.newaxis] # (2x1) 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.T) # 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) # 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)
NN = Neural_Network()
for i in xrange(1000): # trains the NN 1,000 times
print "Input: \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)
The error I am getting is
File "C:/Users/Aaa/AppData/Local/Temp/abc.py", line 43, in backward
self.W1 += X.T.dot(self.z2_delta) # adjusting first set (input --> hidden) weights
AttributeError: 'list' object has no attribute 'T'
