Name
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. |
Year | Venue | DocType |
|---|---|---|
2021 | THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Conference |
Volume | ISSN | Citations |
35 | 2159-5399 | 0 |
PageRank | References | Authors |
0.34 | 0 | 11 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Joel Veness | 1 | 3152 | 152.40 |
| Tor Lattimore | 2 | 174 | 29.15 |
| David Budden | 3 | 167 | 18.45 |
| Avishkar Bhoopchand | 4 | 3 | 1.04 |
| Christopher Mattern | 5 | 3 | 1.04 |
| Agnieszka Grabska-Barwińska | 6 | 272 | 10.12 |
| Sezener Eren | 7 | 0 | 1.69 |
| Jianan Wang | 8 | 51 | 13.82 |
| Peter Toth | 9 | 4 | 2.20 |
| Simon Schmitt | 10 | 12 | 2.19 |
| Marcus Hutter | 11 | 1302 | 132.09 |