Associative Learning Should Go Deep

Mondragon, E., Alonso, E. & Kokkola, N. (2017). Associative Learning Should Go Deep. Trends in Cognitive Science, doi: 10.1016/j.tics.2017.06.001

[img] Text - Accepted Version
Restricted to Repository staff only until 28 June 2018.

Download (1MB) | Request a copy

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.

Item Type: Article
Uncontrolled Keywords: associative learning, deep neural networks
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: School of Informatics > Department of Computing
URI: http://openaccess.city.ac.uk/id/eprint/17684

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics