Scribd
Upload
3 views

AIML Assignment3

The document outlines a Python implementation of a simple neural network for classifying numbers as odd or even using sigmoid activation. It includes the definition of the sigmoid function, the setup of input and output data, and the training process over 10,000 epochs. The final section tests the model on numbers 1 to 10 and prints whether each number is odd or even.

Uploaded by

hipratikshaa13
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

AIML Assignment3

The document outlines a Python implementation of a simple neural network for classifying numbers as odd or even using sigmoid activation. It includes the definition of the sigmoid function, the setup of input and output data, and the training process over 10,000 epochs. The final section tests the model on numbers 1 to 10 and prints whether each number is odd or even.

Uploaded by

hipratikshaa13
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Building a Simple Neural Network for Odd-Even Classification Using Sigmoid Activation

import numpy as np

def sigmoid(x):

return 1 / (1 + np.exp(-x))

def sigmoid_derivative(x):

return x * (1 - x)

X = np.array([[i] for i in range(1, 101)])

y = np.array([[i % 2] for i in range(1, 101)])

np.random.seed(42)

input_size = 1

hidden_size = 2

output_size = 1

learning_rate = 0.1

weights_input_hidden = np.random.rand(input_size, hidden_size)

weights_hidden_output = np.random.rand(hidden_size, output_size)

for epoch in range(10000):

hidden_input = np.dot(X, weights_input_hidden)

hidden_output = sigmoid(hidden_input)

final_input = np.dot(hidden_output, weights_hidden_output)

final_output = sigmoid(final_input)

error = y - final_output
if epoch % 1000 == 0:

loss = np.mean(np.square(error))

print(f'Epoch {epoch}, Loss: {loss}')

output_error = error * sigmoid_derivative(final_output)

hidden_error = output_error.dot(weights_hidden_output.T) * sigmoid_derivative(hidden_output)

weights_hidden_output += hidden_output.T.dot(output_error) * learning_rate

weights_input_hidden += X.T.dot(hidden_error) * learning_rate

test_numbers = np.array([[i] for i in range(1, 11)])

hidden_input = np.dot(test_numbers, weights_input_hidden)

hidden_output = sigmoid(hidden_input)

final_input = np.dot(hidden_output, weights_hidden_output)

final_output = sigmoid(final_input)

for i, num in enumerate(test_numbers):

prediction = final_output[i]

print(f"{num[0]}: {'Odd' if num[0] %2 !=0 else 'Even'}")


OUTPUT:

You might also like