Mondragón E, Alonso E, Kokkola N. Associative Learning Should Go Deep.
Trends Cogn Sci 2017;
21:822-825. [PMID:
28668210 DOI:
10.1016/j.tics.2017.06.001]
[Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2017] [Revised: 05/26/2017] [Accepted: 06/01/2017] [Indexed: 12/20/2022]
Abstract
Conditioning, how animals learn to associate two or more events, is one of the most influential paradigms in learning theory. It is nevertheless unclear how current models of associative learning can accommodate complex phenomena without ad hoc representational assumptions. We propose to embrace deep neural networks to negotiate this problem.
Collapse