Backpropagation

Backpropagation is the learning process many neural networks use to improve after making a prediction. Training begins with a forward pass, in which data moves through the network to produce an output. A loss function then measures how far that output is from the expected result. Working backward through the layers, backpropagation calculates how much each weight contributed to the error. An optimization algorithm uses those gradients to update the weights before the next training example. Repeating this cycle across large datasets gradually reduces error and helps the model recognize useful patterns. The method is central to deep learning, although its effectiveness depends on suitable data, architecture, learning rates, and computational resources.