Biologically-inspired neuronal adaptation improves learning in neural networks

Since humans still outperform artificial neural networks on many tasks, drawing inspiration from the brain may help to improve current machine learning algorithms. Contrastive Hebbian learning (CHL) and equilibrium propagation (EP) are biologically plausible algorithms that update weights using only...

Descripción completa

Detalles Bibliográficos
Autores principales: Kubo, Yoshimasa, Chalmers, Eric, Luczak, Artur
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Taylor & Francis 2023
Materias:
Research Paper
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9851208/
https://www.ncbi.nlm.nih.gov/pubmed/36685291
http://dx.doi.org/10.1080/19420889.2022.2163131

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9851208/
https://www.ncbi.nlm.nih.gov/pubmed/36685291
http://dx.doi.org/10.1080/19420889.2022.2163131

Ejemplares similares