← Library

2026-05-02

1 saved article

  1. Sequential Group Composition: A Window into the Mechanics of Deep Learning

    [Submitted on 3 Feb 2026 (v1), last revised 29 May 2026 (this version, v2)] · arXiv.org

    How do neural networks trained over sequences acquire the ability to perform structured operations, such as arithmetic, geometric, and algorithmic computation? To gain insight into this question, we introduce the sequential group composition task. In this task, networks receive a sequence of elements from a finite group encoded in a real vector space and must predict their cumulative product. This task can be order-sensitive and cannot be solved by a linear model. Our analysis isolates the roles