Brain-inspired replay for continual learning with artificial neural networks

One challenge that faces artificial intelligence is the inability of deep neural networks to continuously learn new information without catastrophically forgetting what has been learnt before. To solve this problem, here the authors propose a replay-based algorithm for deep learning without the need...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gido M. van de Ven, Hava T. Siegelmann, Andreas S. Tolias
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
Q
Acceso en línea:https://doaj.org/article/8cfc2c14df744076b19bf66597cf0559
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:8cfc2c14df744076b19bf66597cf0559
record_format dspace
spelling oai:doaj.org-article:8cfc2c14df744076b19bf66597cf05592021-12-02T15:08:41ZBrain-inspired replay for continual learning with artificial neural networks10.1038/s41467-020-17866-22041-1723https://doaj.org/article/8cfc2c14df744076b19bf66597cf05592020-08-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-17866-2https://doaj.org/toc/2041-1723One challenge that faces artificial intelligence is the inability of deep neural networks to continuously learn new information without catastrophically forgetting what has been learnt before. To solve this problem, here the authors propose a replay-based algorithm for deep learning without the need to store data.Gido M. van de VenHava T. SiegelmannAndreas S. ToliasNature PortfolioarticleScienceQENNature Communications, Vol 11, Iss 1, Pp 1-14 (2020)
institution DOAJ
collection DOAJ
language EN
topic Science
Q
spellingShingle Science
Q
Gido M. van de Ven
Hava T. Siegelmann
Andreas S. Tolias
Brain-inspired replay for continual learning with artificial neural networks
description One challenge that faces artificial intelligence is the inability of deep neural networks to continuously learn new information without catastrophically forgetting what has been learnt before. To solve this problem, here the authors propose a replay-based algorithm for deep learning without the need to store data.
format article
author Gido M. van de Ven
Hava T. Siegelmann
Andreas S. Tolias
author_facet Gido M. van de Ven
Hava T. Siegelmann
Andreas S. Tolias
author_sort Gido M. van de Ven
title Brain-inspired replay for continual learning with artificial neural networks
title_short Brain-inspired replay for continual learning with artificial neural networks
title_full Brain-inspired replay for continual learning with artificial neural networks
title_fullStr Brain-inspired replay for continual learning with artificial neural networks
title_full_unstemmed Brain-inspired replay for continual learning with artificial neural networks
title_sort brain-inspired replay for continual learning with artificial neural networks
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/8cfc2c14df744076b19bf66597cf0559
work_keys_str_mv AT gidomvandeven braininspiredreplayforcontinuallearningwithartificialneuralnetworks
AT havatsiegelmann braininspiredreplayforcontinuallearningwithartificialneuralnetworks
AT andreasstolias braininspiredreplayforcontinuallearningwithartificialneuralnetworks
_version_ 1718388072419164160