Lataa...

Reward-based training of recurrent neural networks for cognitive and value-based tasks

Trained neural network models, which exhibit features of neural activity recorded from behaving animals, may provide insights into the circuit mechanisms of cognitive functions through systematic analysis of network activity and connectivity. However, in contrast to the graded error signals commonly...

Täydet tiedot

Tallennettuna:
Bibliografiset tiedot
Julkaisussa:eLife
Päätekijät: Song, H Francis, Yang, Guangyu R, Wang, Xiao-Jing
Aineistotyyppi: Artigo
Kieli:Inglês
Julkaistu: eLife Sciences Publications, Ltd 2017
Aiheet:
Linkit:https://ncbi.nlm.nih.gov/pmc/articles/PMC5293493/
https://ncbi.nlm.nih.gov/pubmed/28084991
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.7554/eLife.21492
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!