gradient descent

Optimization

Optimization finds model parameters or decisions that best satisfy an objective while respecting practical resource and safety constraints.

May 25, 2026 by Daniel Mercer • 1 min read

Xavier Initialization

Xavier initialization sets neural network weights using layer size to stabilize activations and gradients at the beginning of model training.

Apr 24, 2026 by Marcus Lee • 1 min read

Loss Function

A loss function measures model error during training and gives an optimization algorithm the objective used to adjust AI model parameters.

Apr 14, 2026 by Daniel Mercer • 1 min read

Learning Rate

By Daniel Mercer Apr 7, 2026 • 1 min read

Learning rate is a training hyperparameter that controls how much an AI model changes its weights during each optimization update.

Backpropagation

By Samantha Reed Mar 5, 2026 • 1 min read

Backpropagation trains neural networks by tracing prediction errors backward through their layers and adjusting internal weights to improve future results.

Weight Initialization

By Marcus Lee Feb 27, 2026 • 1 min read

Weight initialization sets the starting parameters of a neural network so activations and gradients remain stable when model training begins.

Gradient Descent

By Daniel Mercer Feb 15, 2026 • 1 min read

Gradient descent is an optimization algorithm that reduces model error by repeatedly adjusting parameters in the direction indicated by the loss gradient.