I am having problem in the Matrix multiplication of my Python neural network. Being still a High schooler, I know next to nothing about MM except a couple of tutorials. My Neural network was working fine when my inputs were like ([0,1,1]...) but when I changed them to doubles, my MM is going wrong(No Output)

# The initialization
import numpy as np
iterations = int(0)


def sigmoid(x):
   return 1/(1 + np.exp(-x))

#The function- 2

def Sigmoid_Derivative(x):
    return sigmoid(x) * (1-sigmoid(x))

Training_inputs = np.array([[0,0], 
                            [0,1]])          # 4 rows * 2 columns

Training_outputs = np.array([[1, 1, 
                              0, 0]]).T               # 2 rows * 2 columns

Correct_Outputs = np.array([[[1],[1],


synaptic_weights = np.random.random((2, 1)) - 1

print ("Random starting synaptic weight:")
print (synaptic_weights)

for iteration in range(20000):
  Input_Layer = Training_inputs

  Outputs = sigmoid(np.dot(Input_Layer, synaptic_weights)) 
  erorr = Training_outputs - Outputs
  adjustments = erorr * Sigmoid_Derivative(Outputs)
  synaptic_weights += np.dot(Input_Layer.T, adjustments)

  Rounder = np.around([np.array(Outputs)],decimals = 2,)
  Final_Outputs = Rounder.astype(int)
  iterations += 1

  if np.array_equal(Final_Outputs, Correct_Outputs):
       print ("Synaptic weights after trainig:")
       print (synaptic_weights)

       print ("Outputs after training: ")
       print (Outputs)

       print ("NO. of iterations required: ",iterations)

P.S The if-else iteration checker was my own coding. Maybe it might have a potential implication.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.