Scribd
Upload
15 views3 pages

AIML Assignment 3

The document outlines a Python implementation of a simple neural network for classifying numbers as odd or even using sigmoid activation. It includes the setup of input and output data, the initialization of weights, and the training process over 10,000 epochs with error calculation and weight updates. Finally, it tests the model on numbers 1 to 10 and prints whether each number is odd or even based on the predictions.

Uploaded by

hipratikshaa13
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
15 views3 pages

AIML Assignment 3

The document outlines a Python implementation of a simple neural network for classifying numbers as odd or even using sigmoid activation. It includes the setup of input and output data, the initialization of weights, and the training process over 10,000 epochs with error calculation and weight updates. Finally, it tests the model on numbers 1 to 10 and prints whether each number is odd or even based on the predictions.

Uploaded by

hipratikshaa13
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

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