Cargando…

Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning

The ability to acquire abstract knowledge is a hallmark of human intelligence and is believed by many to be one of the core differences between humans and neural network models. Agents can be endowed with an inductive bias towards abstraction through meta-learning, where they are trained on a distri...

Descripción completa

Detalles Bibliográficos
Autores principales: Kumar, Sreejan, Dasgupta, Ishita, Daw, Nathaniel D., Cohen, Jonathan. D., Griffiths, Thomas L.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10497163/
https://www.ncbi.nlm.nih.gov/pubmed/37624841
http://dx.doi.org/10.1371/journal.pcbi.1011316