AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Transformation Laws in Neural Representations: Structure, Realisability, and Construction

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

How neural representations preserve the structure of input changes connects representation analysis with internal intervention. We study operable representational content through compatible actions of reference transformations on neural features. We characterise when a transformation descends through an encoder, and give a linear setting in which the defect is governed by the transformation's demand for discarded information, measured in the metric the representation induces. On a rectifier the failure to realise a transformation has two distinguishable sources --- what the source region has a

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T08:01:03.945Z. This is not the publication date.