Re How Attention Can Create Synaptic Tags for the Learning of Working Memories in Sequential TasksReportar como inadecuado




Re How Attention Can Create Synaptic Tags for the Learning of Working Memories in Sequential Tasks - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 Mnemosyne - Mnemonic Synergy LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives Bordeaux

Abstract : The reference paper introduces a new reinforcement learning model called Attention-Gated MEmory Tagging AuGMEnT. The results presented suggest new approachesin understanding the acquisition of tasks requiring working memory and attentionalfeedback, as well as biologically plausible learning mechanisms. The model also improveson previous reinforcement learning schemes by allowing tasks to be expressedmore naturally as a sequence of inputs and outputs.A Python implementation of the model is available on the author’s GitHub pagewhich helped to verify the correctness of the computations. The script written forthis replication also uses Python along with NumPy.





Autor: Erwan Le Masson - Frédéric Alexandre -

Fuente: https://hal.archives-ouvertes.fr/



DESCARGAR PDF




Documentos relacionados