Notes

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset
import pandas as pd
import matplotlib.pyplot as plt

# Define the MLP model
class MLP(nn.Module):
def __init__(self):
super(MLP, self).__init__()
self.fc1 = nn.Linear(2, 8) # First hidden layer
self.fc2 = nn.Linear(8, 8) # Second hidden layer
self.fc3 = nn.Linear(8, 1) # Output layer

def forward(self, x):
x = torch.relu(self.fc1(x)) # ReLU activation
x = torch.relu(self.fc2(x)) # ReLU activation
x = torch.sigmoid(self.fc3(x)) # Sigmoid activation
return x

# Initialize the model, loss function, and optimizer
model = MLP()
criterion = nn.BCELoss() # Binary Cross-Entropy Loss
optimizer = optim.Adam(model.parameters(), lr=0.01)

# Define the XOR gate input and output
X_train = torch.tensor([[0.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 1.0]])
y_train = torch.tensor([[0.0], [1.0], [1.0], [0.0]])

# Create a DataLoader
dataset = TensorDataset(X_train, y_train)
dataloader = DataLoader(dataset, batch_size=4, shuffle=True)

# Train the model
num_epochs = 1000
for epoch in range(num_epochs):
for batch_X, batch_y in dataloader:
optimizer.zero_grad()
outputs = model(batch_X)
loss = criterion(outputs, batch_y)
loss.backward()
optimizer.step()

if (epoch+1) % 100 == 0:
print(f'Epoch [{epoch + 1}/{num_epochs}], Loss: {loss.item()}')

# Evaluate the model
with torch.no_grad():
model.eval()
outputs = model(X_train)
binary_predictions = (outputs > 0.5).float().numpy().flatten() # Apply threshold for binary output
y_train = y_train.numpy().flatten()

# Create a DataFrame to display results
results_df = pd.DataFrame({
'Input': [f'{x[0]}, {x[1]}' for x in X_train.numpy()],
'Actual Output': y_train,
'Predicted Output': binary_predictions
})

print(results_df)

# Plotting the results
plt.figure(figsize=(10, 6))
plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train, s=100, edgecolor='k', label='Actual Output', cmap='viridis')
plt.scatter(X_train[:, 0], X_train[:, 1], c=binary_predictions, marker='x', s=100, label='Predicted Output', cmap='coolwarm')
plt.xlabel('Input Feature 1')
plt.ylabel('Input Feature 2')
plt.title('XOR Gate: Actual vs. Predicted Outputs')
plt.legend()
plt.grid(True)
plt.show()