Vocabulary

Understand the term. Connect the concept.

A practical dictionary of 512 AI, machine learning, mathematics, and programming terms from HerbDev’s AI Vocabulary app. Start with a definition, explore an example, then follow the concepts behind it.

Linked concepts open in a new tab. Audio reads the definition and example.

Weight Decay

Optimization · Level 2 of 5

Weight Decay

A regularization update that shrinks parameter values toward zero.

Decoupled weight decay is not identical to adding L2 loss for every optimizer.

Example

Each optimizer step slightly reduces weights in addition to the gradient update.

Listen to the definition and example

Audio transcript

Weight Decay. A regularization update that shrinks parameter values toward zero. Decoupled weight decay is not identical to adding L2 loss for every optimizer. For example: Each optimizer step slightly reduces weights in addition to the gradient update.

Explore this concept

Why it matters

This helps you understand what parameter updates are trying to improve and when they can fail.

Start with

Related concepts

Quick recall question

Try answering before looking back at the definition.

Put the terminology into context: How AI works · Machine-native representations · All learning paths

Manage browser learning data

“Remove my test data” clears all AI 101 and ML 101 scores, reviews, project checklists and rating selections, plus saved vocabulary and recent history in this browser. Test entries cannot be separated from other learning progress. Cookie preferences, security protections, submitted feedback, contact emails and past analytics are kept.