backprop-computes-gradient-not-learning

IN premise — entries/2026/06/21/wiki-Backpropagation-chunk-7.md

Created 2026-06-21T09:55:49+00:00

Backpropagation only computes the gradient; a separate optimization algorithm (e.g., SGD, Adam) performs the actual parameter updates.

Dependents

These beliefs depend on this one:

• OUT gradient-descent-effective-global-optimizer — Gradient descent with backpropagation effectively finds global optima for neural network training in practice, despite lacking global guarantees.
• IN gradient-learning-connects-autodiff-optimization-dynamics — Gradient-based neural network training sits at the intersection of three mathematical frameworks: reverse-mode automatic differentiation (backprop), iterative optimization (gradient descent), and continuous dynamical systems (gradient flow ODE).