Priors in Animal and Artificial Intelligence: Where Does Learning Begin?

被引：37

作者：

Versace, Elisabetta ^{[1
]}

Martinho-Truswell, Antone ^{[2
]}

Kacelnik, Alex ^{[2
]}

Vallortigara, Giorgio ^{[3
]}

机构：

[1] Queen Mary Univ London, Sch Biol & Chem Sci, Dept Biol & Expt Psychol, Mile End Rd, London E1 4NS, England

[2] Univ Oxford, Dept Zool, New Radcliffe House, Oxford OX1 3PS, England

[3] Univ Trento, Ctr Mind Brain Sci, Piazza Manifattura 1, Rovereto, Italy

来源：

TRENDS IN COGNITIVE SCIENCES | 2018年 / 22卷 / 11期

基金：

欧洲研究理事会;

关键词：

CHICKS; PATTERNS; OBJECT;

D O I：

10.1016/j.tics.2018.07.005

中图分类号：

B84 [心理学]; C [社会科学总论]; Q98 [人类学];

学科分类号：

03 ; 0303 ; 030303 ; 04 ; 0402 ;

摘要：

A major goal for the next generation of artificial intelligence (AI) is to build machines that are able to reason and cope with novel tasks, environments, and situations in a manner that approaches the abilities of animals. Evidence from precocial species suggests that driving learning through suitable priors can help to successfully face this challenge.

引用

页码：963 / 965

页数：3

共 14 条

[1]

[Anonymous], 2004, BLANK SLATE MODERN D

[2] SEXUAL IMPRINTING AND OPTIMAL OUTBREEDING [J].