02/02/2021

Gated Linear Networks

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

Keywords:

Abstract Paper Similar Papers

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.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948489
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 5:08 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 1
 12:45 
 0
 0
 0
 0
 5:26 
 0
 0
 0
 0
 15:07 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 3:28 
 0
 0
 0
 0
 4:34 
 0
 0
 0
 0
 4:20 
 0
 0
 0
 0
 3:58 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 11:01 
 0
 0
 0
 1
 3:15 
 0
 0
 0
 0
 0:59 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 17:12 
 0
 0
 0
 0
 16:27 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 7:57 
 0
 0
 0
 0
 15:05 
 1
 0
 1
 0
 5:08 
 0
 0
 0
 0
 13:28 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 14:18 
 0
 0
 0
 0
 3:27 
 0
 0
 0
 0
 11:09 
 0
 0
 0
 0
 13:40 
 0
 0
 0
 0
 3:26 
 0
 0
 0
 0
 13:29 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 13:33