← Blog

Backpropagation

DL

/dictionary/backpropagation

Definition

The algorithm that computes how each parameter in a neural network should be adjusted to reduce the loss. It walks the error backwards through every layer using the chain rule. Combined with gradient descent, it is how networks learn.

Posts that use this term

  • How a model learns: training and inference

    Training is the expensive one-time event where a model's numbers get tuned. Inference is the cheap repeated use afterwards. The gap in cost is enormous, and it shapes the whole industry.