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...

Cijeli opis

Spremljeno u:
Bibliografski detalji
Izdano u:Proc Natl Acad Sci U S A
Glavni autori: 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
Format: Artigo
Jezik:Inglês
Izdano: National Academy of Sciences 2017
Teme:
Biological Sciences
Online pristup: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
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!

Similar Items