Metadata only
Datum
2024-07Typ
- Conference Paper
ETH Bibliographie
yes
Altmetrics
Abstract
Online learning holds the promise of enabling efficient long-term credit assignment in recurrent neural networks. However, current algorithms fall short of offline backpropagation by either not being scalable or failing to learn long-range dependencies. Here we present a high-performance online learning algorithm that merely doubles the memory and computational requirements of a single inference pass. We achieve this by leveraging independent recurrent modules in multi-layer networks, an architectural motif that has recently been shown to be particularly powerful. Experiments on synthetic memory problems and on the challenging long-range arena benchmark suite reveal that our algorithm performs competitively, establishing a new standard for what can be achieved through online learning. This ability to learn long-range dependencies offers a new perspective on learning in the brain and opens a promising avenue in neuromorphic computing. Mehr anzeigen
Publikationsstatus
publishedExterne Links
Herausgeber(in)
Buchtitel
Advances in Neural Information Processing Systems 36Seiten / Artikelnummer
Verlag
CurranKonferenz
Thema
Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); FOS: Computer and information sciencesOrganisationseinheit
03672 - Steger, Angelika / Steger, Angelika
Zugehörige Publikationen und Daten
Is new version of: https://openreview.net/forum?id=Wa1GGPqjUn
Anmerkungen
Poster presented on December 12, 2023.ETH Bibliographie
yes
Altmetrics