Theory of Gating in Recurrent Neural Networks

Recurrent neural networks (RNNs) are powerful dynamical models, widely used in machine learning (ML) and neuroscience. Prior theoretical work has focused on RNNs with additive interactions. However gating i.e., multiplicative interactions are ubiquitous in real neurons and also the central feature o...

Descripción completa

Detalles Bibliográficos
Autores principales: Krishnamurthy, Kamesh, Can, Tankut, Schwab, David J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9762509/
https://www.ncbi.nlm.nih.gov/pubmed/36545030
http://dx.doi.org/10.1103/physrevx.12.011011

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9762509/
https://www.ncbi.nlm.nih.gov/pubmed/36545030
http://dx.doi.org/10.1103/physrevx.12.011011

Ejemplares similares