Skip to main content
HT
HerbDev Application Rescue
← Learning hub

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.

Bias

Neural Networks · Level 2 of 5

Bias

A learned offset added to a computation independently of its current input.

A neural bias parameter differs from statistical bias or societal bias.

Example

A unit adds a constant before applying its activation.

Listen to the definition and example

Audio transcript

Bias. A learned offset added to a computation independently of its current input. A neural bias parameter differs from statistical bias or societal bias. For example: A unit adds a constant before applying its activation.

Explore this concept

A useful analogy

An adjustable starting offset before any input contribution is added.

Why it matters

This is part of the vocabulary used to read network diagrams and understand parameter updates.

Technical detail

In z = Wx + b, b shifts the affine transformation. Without b the map is linear through the origin.

Common misconception

A neural bias parameter is different from societal bias or estimator bias.

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.