How does backpropagation work in training neural networks?

Backpropagation is a method for updating neural network weights to minimize errors. It involves:
1. Forward Pass: Calculate predictions.
2. Loss Computation: Measure the error between predictions and actual values.
3. Backward Pass: Compute gradients of the loss function with respect to each weight using the chain rule.
4. Weight Update: Adjust weights using an optimization algorithm like gradient descent. This iterative process trains the network.