Topologies of learning and development

被引：48

作者：

Bickhard, MH ^{[1
]}

Campbell, RL ^{[1
]}

机构：

[1] CLEMSON UNIV, DEPT PSYCHOL, CLEMSON, SC 29634 USA

来源：

NEW IDEAS IN PSYCHOLOGY | 1996年 / 14卷 / 02期

关键词：

D O I：

10.1016/0732-118X(96)00015-3

中图分类号：

B84 [心理学];

学科分类号：

04 ; 0402 ;

摘要：

How systems can represent and how systems can learn are two central problems in the study of cognition. Conventional contemporary approaches to these problems are vitiated by a shared error in their presuppositions about representation Consequently, such approaches share further errors about the sorts of architectures that are required to support either representation or learning. We argue that the architectural requirements for genuine representing systems lead to architectural characteristics that are necessary (though not sufficient) for heuristic learning and development These architectural constraints, in turn, explain properties of the functioning of the central nervous system that remain inexplicable for standard approaches. Copyright (C) 1996 Elsevier Science Ltd

引用

页码：111 / 156

页数：46

共 50 条

[11] Active Learning of Multiple Source Multiple Destination Topologies
Sattari, Pegah
Kurant, Maciej
Anandkumar, Animashree
Markopoulou, Athina
Rabbat, Michael G.
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2014, 62 (08) : 1926 - 1937
[12] LEARNING TO INFER POWER GRID TOPOLOGIES: PERFORMANCE AND SCALABILITY
Zhao, Yue
Chen, Jianshu
Poor, H. Vincent
2018 IEEE DATA SCIENCE WORKSHOP (DSW), 2018, : 215 - 219
[13] Social Learning in Networks with Time-Varying Topologies
Liu, Qipeng
Wang, Xiaofan
2012 IEEE 51ST ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2012, : 1972 - 1977
[14] An online learning algorithm for adaptable topologies of neural networks
Perez-Sanchez, Beatriz
Fontenla-Romero, Oscar
Guijarro-Berdinas, Bertha
Martinez-Rego, David
EXPERT SYSTEMS WITH APPLICATIONS, 2013, 40 (18) : 7294 - 7304
[15] Active Learning of Multiple Source Multiple Destination Topologies
Sattari, Pegah
Kurant, Maciej
Anandkumar, Animashree
Markopoulou, Athina
Rabbat, Michael
2013 47TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS), 2013,
[16] Learning on Arbitrary Graph Topologies via Predictive Coding
Salvatori, Tommaso
Pinchetti, Luca
Millidge, Beren
Song, Yuhang
Bao, Tianyi
Bogacz, Rafal
Lukasiewicz, Thomas
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
[17] Learning to cooperate: Networks of formation agents with switching topologies
Meng, Deyuan
Moore, Kevin L.
AUTOMATICA, 2016, 64 : 278 - 293
[18] Optimizing deep learning RNN topologies on intel architecture
Banerjee K.
Georganas E.
Kalamkar D.D.
Ziv B.
Segal E.
Anderson C.
Heinecke A.
Supercomputing Frontiers and Innovations, 2019, 6 (03) : 64 - 85
[19] Parallell interacting MCMC for learning of topologies of graphical models
Corander, Jukka
Ekdahl, Magnus
Koski, Timo
DATA MINING AND KNOWLEDGE DISCOVERY, 2008, 17 (03) : 431 - 456
[20] Putting the individual in context: paths, capitals and topologies of learning
Faulconbridge, James
PROMETHEUS, 2014, 32 (01) : 75 - 82

← 1 2 3 4 5 →