Neural Networks 101

A neural network is a computational model inspired by the brain's structure.

Architecture

• Input layer: Receives raw data
• Hidden layers: Transform data through weighted connections
• Output layer: Produces predictions

Key Concepts

• Weights are adjusted during training
• Activation functions (ReLU, sigmoid) add non-linearity
• Backpropagation computes gradients for optimization

import torch.nn as nn

model = nn.Sequential(
    nn.Linear(784, 128),
    nn.ReLU(),
    nn.Linear(128, 10)
)