A constructive neural-network approach to modeling psychological development

被引：12
作者：
Shultz, Thomas R. [1 ,2 ]
机构：
[1] McGill Univ, Dept Psychol, Montreal, PQ H3A 1B1, Canada
[2] McGill Univ, Sch Comp Sci, Montreal, PQ H3A 1B1, Canada
来源：
COGNITIVE DEVELOPMENT | 2012年 / 27卷 / 04期
基金：
加拿大自然科学与工程研究理事会;
关键词：
Computational modeling; Constructive neural networks; Psychological development; Cascade-correlation; COGNITIVE-DEVELOPMENT; DISTANCE; INFORMATION; SERIATION; VELOCITY; TIME;
D O I：
10.1016/j.cogdev.2012.08.002
中图分类号：
B844 [发展心理学（人类心理学）];
学科分类号：
040202 ;
摘要：
This article reviews a particular computational modeling approach to the study of psychological development - that of constructive neural networks. This approach is applied to a variety of developmental domains and issues, including Piagetian tasks, shift learning, language acquisition, number comparison, habituation of visual attention, concept learning, and theory of mind. Implications of this modeling for theoretical understanding of psychological development are considered. (C) 2012 Elsevier Inc. All rights reserved.
引用
收藏
页码：383 / 400
页数：18
相关论文
共 67 条
[51]  
Shultz TR, 2006, ATTENTION PERFORM, P61
[52]   Neural networks discover a near-identity relation to distinguish simple syntactic forms [J].
Shultz, Thomas R. ;
Bale, Alan C. .
MINDS AND MACHINES, 2006, 16 (02) :107-139
[53]  
Shultz TR, 2008, CAMB HANDB PSYCHOL, P451
[54]   Neural Network Simulation of Infant Familiarization to Artificial Sentences: Rule-Like Behavior Without Explicit Rules and Variables [J].
Shultz, Thomas R. ;
Bale, Alan C. .
INFANCY, 2001, 2 (04) :501-536
[55]   A computational analysis of conservation [J].
Shultz, Thomas R. .
DEVELOPMENTAL SCIENCE, 1998, 1 (01) :103-126
[56]   MODELING COGNITIVE-DEVELOPMENT ON BALANCE SCALE PHENOMENA [J].
SHULTZ, TR ;
MARESCHAL, D ;
SCHMIDT, WC .
MACHINE LEARNING, 1994, 16 (1-2) :57-86
[57]   Modeling age differences in infant category learning [J].
Shultz, TR ;
Cohen, LB .
INFANCY, 2004, 5 (02) :153-171
[58]   Knowledge-based cascade-correlation: using knowledge to speed learning [J].
Shultz, TR ;
Rivest, F .
CONNECTION SCIENCE, 2001, 13 (01) :43-72
[59]  
SHULTZ TR, 1994, COMPUTATIONAL LEARNING THEORY AND NATURAL LEARNING SYSTEMS, VOL II: INTERSECTIONS BETWEEN THEORY AND EXPERIMENT, P347
[60]  
SIEGLER RS, 1981, MONOGRAPHS SOC RES C, V46
1234567