Editing Neural Networks (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''Training a simple neural network in PyTorch:'''

<syntaxhighlight lang="python">
import torch
import torch.nn as nn
import torch.optim as optim

# Define a simple 3-layer feedforward network
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.layers = nn.Sequential(
            nn.Linear(784, 256),   # Input: 28x28 image flattened
            nn.ReLU(),
            nn.Dropout(0.3),
            nn.Linear(256, 128),
            nn.ReLU(),
            nn.Linear(128, 10)     # Output: 10 classes
        )

    def forward(self, x):
        return self.layers(x)

model = SimpleNet()
optimizer = optim.Adam(model.parameters(), lr=1e-3)
criterion = nn.CrossEntropyLoss()

# Training loop
for epoch in range(10):
    for batch_x, batch_y in dataloader:
        optimizer.zero_grad()
        predictions = model(batch_x)
        loss = criterion(predictions, batch_y)
        loss.backward()       # Backpropagation
        optimizer.step()      # Weight update
    print(f"Epoch {epoch+1}, Loss: {loss.item():.4f}")
</syntaxhighlight>

; Key hyperparameters to tune
: '''Learning rate''' — Start with 1e-3 for Adam, 1e-1 for SGD. Use a scheduler to decay over time.
: '''Batch size''' — 32 or 64 is a good default. Larger batches train faster but may generalize worse.
: '''Network depth''' — Start shallow (2–3 layers), deepen only if underfitting.
: '''Dropout rate''' — 0.2–0.5 for hidden layers; never apply to the output layer.
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">