Overcoming catastrophic forgetting in neural networks

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possib...

Descrizione completa

Salvato in:
Dettagli Bibliografici
Pubblicato in:Proc Natl Acad Sci U S A
Autori principali: Kirkpatrick, James, Pascanu, Razvan, Rabinowitz, Neil, Veness, Joel, Desjardins, Guillaume, Rusu, Andrei A., Milan, Kieran, Quan, John, Ramalho, Tiago, Grabska-Barwinska, Agnieszka, Hassabis, Demis, Clopath, Claudia, Kumaran, Dharshan, Hadsell, Raia
Natura: Artigo
Lingua:Inglês
Pubblicazione: National Academy of Sciences 2017
Soggetti:
Biological Sciences
Accesso online:https://ncbi.nlm.nih.gov/pmc/articles/PMC5380101/
https://ncbi.nlm.nih.gov/pubmed/28292907
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1073/pnas.1611835114
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne! !

Documenti analoghi