You On AI Field Guide · Invariants The You On AI Field Guide Home
Txt Low Med High
CONCEPT

Invariants

The properties of the ambient array that persist unchanged across transformations generated by the observer's movement — the information the organism extracts through active perception, and the structural feature Gibson identified as what perception actually detects.
Invariants are the mathematical heart of Gibson's theory. As the observer moves through the environment, the ambient optic array transforms continuously: textures expand and contract, surfaces rotate in perspective, occlusion boundaries shift. Amid these transformations, certain higher-order properties remain unchanged — the ratio between the observer's height and the apparent elevation of distant objects, the rate of change of a texture gradient, the topological relationships among surfaces. These invariants specify the layout of the environment with mathematical precision. Perception, in Gibson's account, is the detection of invariants: the perceptual system extracts what persists across transformations rather than processing each momentary array as an independent stimulus. The concept is what makes direct perception mathematically tenable — the information is not merely suggestive of the environment's structure; it specifies that structure through the invariants that emerge in the flow of exploratory action.

In The You On AI Field Guide

The discovery that invariants carry information about environmental structure was the mathematical breakthrough that allowed

← Home 0%
CONCEPT Book →

Keep reading with YOU ON AI

Unlock the full book, 10,000+ field-guide entries, and a 1000+ thinker library. If you have a book code, register now — it takes a minute.

Register with book code Sign in