English

Gated Linear Networks

Machine Learning 2020-06-12 v2 Information Theory math.IT Machine Learning

Abstract

This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). What distinguishes GLNs from contemporary neural networks is the distributed and local nature of their credit assignment mechanism; each neuron directly predicts the target, forgoing the ability to learn feature representations in favor of rapid online learning. Individual neurons can model nonlinear functions via the use of data-dependent gating in conjunction with online convex optimization. We show that this architecture gives rise to universal learning capabilities in the limit, with effective model capacity increasing as a function of network size in a manner comparable with deep ReLU networks. Furthermore, we demonstrate that the GLN learning mechanism possesses extraordinary resilience to catastrophic forgetting, performing comparably to a MLP with dropout and Elastic Weight Consolidation on standard benchmarks. These desirable theoretical and empirical properties position GLNs as a complementary technique to contemporary offline deep learning methods.

Keywords

Cite

@article{arxiv.1910.01526,
  title  = {Gated Linear Networks},
  author = {Joel Veness and Tor Lattimore and David Budden and Avishkar Bhoopchand and Christopher Mattern and Agnieszka Grabska-Barwinska and Eren Sezener and Jianan Wang and Peter Toth and Simon Schmitt and Marcus Hutter},
  journal= {arXiv preprint arXiv:1910.01526},
  year   = {2020}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1712.01897

R2 v1 2026-06-23T11:33:50.456Z