Cargando…

Representational Distance Learning for Deep Neural Networks

Deep neural networks (DNNs) provide useful models of visual representational transformations. We present a method that enables a DNN (student) to learn from the internal representational spaces of a reference model (teacher), which could be another DNN or, in the future, a biological brain. Represen...

Descripción completa

Detalles Bibliográficos
Autores principales: McClure, Patrick, Kriegeskorte, Nikolaus
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5187453/
https://www.ncbi.nlm.nih.gov/pubmed/28082889
http://dx.doi.org/10.3389/fncom.2016.00131