The local is running on the express track: Localist models better facilitate understanding of nervous system function

Paul A. Koch; Gerry Leisman

doi:10.1017/s0140525x04260162

The local is running on the express track: Localist models better facilitate understanding of nervous system function

Research output: Contribution to journal › Article › peer-review

Abstract

Artificial neural networks have weaknesses as models of cognition. A conventional neural network has limitations of computational power. The localist representation is at least equal to its competition. We contend that locally connected neural networks are perfectly capable of storing and retrieving the individual features, but the process of reconstruction must be otherwise explained. We support the localist position but propose a "hybrid" model that can begin to explain cognition in anatomically plausible terms.

Original language	English
Pages (from-to)	700
Number of pages	1
Journal	Behavioral and Brain Sciences
Volume	27
Issue number	5
DOIs	https://doi.org/10.1017/s0140525x04260162
State	Published - Oct 2004
Externally published	Yes

Bibliographical note

Funding Information:
The authors acknowledge The Committee of National Science Fund for financial support (project 59934080).

ASJC Scopus subject areas

Neuropsychology and Physiological Psychology
Physiology
Behavioral Neuroscience

Access to Document

10.1017/s0140525x04260162

Cite this

@article{e9cc2db8313c4bd8a83b968fcd961bbb,

title = "The local is running on the express track: Localist models better facilitate understanding of nervous system function",

abstract = "Artificial neural networks have weaknesses as models of cognition. A conventional neural network has limitations of computational power. The localist representation is at least equal to its competition. We contend that locally connected neural networks are perfectly capable of storing and retrieving the individual features, but the process of reconstruction must be otherwise explained. We support the localist position but propose a {"}hybrid{"} model that can begin to explain cognition in anatomically plausible terms.",

author = "Koch, {Paul A.} and Gerry Leisman",

note = "Funding Information: The authors acknowledge The Committee of National Science Fund for financial support (project 59934080).",

year = "2004",

month = oct,

doi = "10.1017/s0140525x04260162",

language = "English",

volume = "27",

pages = "700",

journal = "Behavioral and Brain Sciences",

issn = "0140-525X",

publisher = "Cambridge University Press",

number = "5",

}

TY - JOUR

T1 - The local is running on the express track

T2 - Localist models better facilitate understanding of nervous system function

AU - Koch, Paul A.

AU - Leisman, Gerry

N1 - Funding Information: The authors acknowledge The Committee of National Science Fund for financial support (project 59934080).

PY - 2004/10

Y1 - 2004/10

N2 - Artificial neural networks have weaknesses as models of cognition. A conventional neural network has limitations of computational power. The localist representation is at least equal to its competition. We contend that locally connected neural networks are perfectly capable of storing and retrieving the individual features, but the process of reconstruction must be otherwise explained. We support the localist position but propose a "hybrid" model that can begin to explain cognition in anatomically plausible terms.

AB - Artificial neural networks have weaknesses as models of cognition. A conventional neural network has limitations of computational power. The localist representation is at least equal to its competition. We contend that locally connected neural networks are perfectly capable of storing and retrieving the individual features, but the process of reconstruction must be otherwise explained. We support the localist position but propose a "hybrid" model that can begin to explain cognition in anatomically plausible terms.

UR - http://www.scopus.com/inward/record.url?scp=17544377309&partnerID=8YFLogxK

U2 - 10.1017/s0140525x04260162

DO - 10.1017/s0140525x04260162

M3 - Article

AN - SCOPUS:17544377309

SN - 0140-525X

VL - 27

SP - 700

JO - Behavioral and Brain Sciences

JF - Behavioral and Brain Sciences

IS - 5

ER -

The local is running on the express track: Localist models better facilitate understanding of nervous system function

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this