Manneschi, L. and Vasilaki, E. orcid.org/0000-0003-3705-7070 (2020) An alternative to backpropagation through time. Nature Machine Intelligence, 2 (3). pp. 155-156.
Abstract
Recurrent networks can be trained using a generalization of backpropagation, called backpropagation through time, but a gap exists between the mathematics of this learning algorithm and biological plausibility. E-prop is a biologically inspired alternative that opens up possibilities for a new generation of online training algorithms for recurrent networks.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2020 The Authors. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 15 Feb 2021 11:07 |
Last Modified: | 15 Feb 2021 11:07 |
Status: | Published |
Publisher: | Springer Nature |
Refereed: | Yes |
Identification Number: | 10.1038/s42256-020-0162-9 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:171064 |
Download not available
A full text copy of this item is not currently available from White Rose Research Online