Optimal performance of a feed-forward network at statistical discrimination tasks

W. Bialek; R. Scalettar; A. Zee

doi:10.1007/BF01023637

Optimal performance of a feed-forward network at statistical discrimination tasks

W. Bialek, R. Scalettar, A. Zee

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

2 Scopus citations

Abstract

Within the context of a particular statistical discrimination task, we make a quantitative comparison between the performance of a feed-forward neural network and the information-theoretic optimal performance. We also address the ability of such networks to generalize and the effect of network architecture on performance.

Original language	English (US)
Pages (from-to)	141-156
Number of pages	16
Journal	Journal of Statistical Physics
Volume	57
Issue number	1-2
DOIs	https://doi.org/10.1007/BF01023637
State	Published - Oct 1989
Externally published	Yes

All Science Journal Classification (ASJC) codes

Statistical and Nonlinear Physics
Mathematical Physics

Keywords

Neural network
information theory
optimal performance
statistical discrimination
visual system

Access to Document

10.1007/BF01023637

Cite this

@article{0ea952b9da18476e9d3dc270fd621e58,

title = "Optimal performance of a feed-forward network at statistical discrimination tasks",

abstract = "Within the context of a particular statistical discrimination task, we make a quantitative comparison between the performance of a feed-forward neural network and the information-theoretic optimal performance. We also address the ability of such networks to generalize and the effect of network architecture on performance.",

keywords = "Neural network, information theory, optimal performance, statistical discrimination, visual system",

author = "W. Bialek and R. Scalettar and A. Zee",

year = "1989",

month = oct,

doi = "10.1007/BF01023637",

language = "English (US)",

volume = "57",

pages = "141--156",

journal = "Journal of Statistical Physics",

issn = "0022-4715",

publisher = "Springer",

number = "1-2",

}

TY - JOUR

T1 - Optimal performance of a feed-forward network at statistical discrimination tasks

AU - Bialek, W.

AU - Scalettar, R.

AU - Zee, A.

PY - 1989/10

Y1 - 1989/10

N2 - Within the context of a particular statistical discrimination task, we make a quantitative comparison between the performance of a feed-forward neural network and the information-theoretic optimal performance. We also address the ability of such networks to generalize and the effect of network architecture on performance.

AB - Within the context of a particular statistical discrimination task, we make a quantitative comparison between the performance of a feed-forward neural network and the information-theoretic optimal performance. We also address the ability of such networks to generalize and the effect of network architecture on performance.

KW - Neural network

KW - information theory

KW - optimal performance

KW - statistical discrimination

KW - visual system

UR - https://www.scopus.com/pages/publications/34249975265

UR - https://www.scopus.com/inward/citedby.url?scp=34249975265&partnerID=8YFLogxK

U2 - 10.1007/BF01023637

DO - 10.1007/BF01023637

M3 - Article

AN - SCOPUS:34249975265

SN - 0022-4715

VL - 57

SP - 141

EP - 156

JO - Journal of Statistical Physics

JF - Journal of Statistical Physics

IS - 1-2

ER -

Optimal performance of a feed-forward network at statistical discrimination tasks

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this