Gated Linear Networks

Authors

  • Joel Veness Deepmind
  • Tor Lattimore DeepMind
  • David Budden DeepMind
  • Avishkar Bhoopchand DeepMind
  • Christopher Mattern DeepMind
  • Agnieszka Grabska-Barwinska DeepMind
  • Eren Sezener DeepMind
  • Jianan Wang DeepMind
  • Peter Toth DeepMind
  • Simon Schmitt DeepMind
  • Marcus Hutter DeepMind

Keywords:

(Deep) Neural Network Algorithms

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 are able to 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 almost on par to an MLP with dropout and Elastic Weight Consolidation on standard benchmarks.

Downloads

Published

2021-05-18

How to Cite

Veness, J., Lattimore, T., Budden, D., Bhoopchand, A., Mattern, C., Grabska-Barwinska, A., Sezener, E., Wang, J., Toth, P., Schmitt, S., & Hutter, M. (2021). Gated Linear Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 10015-10023. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17202

Issue

Section

AAAI Technical Track on Machine Learning IV