arrow
返回

Associative Learning Should Go Deep

delete2017-11-01
delete10
delete
OA
AI
E
Esther Mondragón
E
Eduardo Alonso
N
Niklas H. Kokkola *
DOI:10.1016/j.tics.2017.06.001delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
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.
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Trends in Cognitive Sciences 封面图
Trends in Cognitive Sciences
IF:
17.2
论文数:
3.6K
被引数:
3.5W

机构

U
university of london
学者数:
21.5W
论文数: 19.7W
被引数: 305
引用论文

引用论文

Grounding Cognitive Control in Associative Learning
err2016-07-01
err211
PREAI
errAbrahamse, Elger; Braem, Senne; Notebaert, Wim; Verguts, Tom
err分享
err收藏
CELL AND MOLECULAR BIOLOGY Trial and error
errSCIENCE
IF45.8
err2016-12-02
err2
PREAI
errEshel, Neir
err分享
err收藏
Highly sensitive 26Al measurements by Ion-Laser-InterAction Mass Spectrometry
err2021-07-01
err0
errOAAI
errJohannes Lachner; Martin Martschini; Andreas Kalb; Michael Kern; Oscar Marchhart; Felix Plasser; Alfred Priller; Peter Steier; Alexander Wieser; Robin Golser
err分享
err收藏
没有更多内容