ON MATHEMATICAL METHODS IN THE THEORY OF NEURAL NETWORKS.

Shun ichi Amari

ON MATHEMATICAL METHODS IN THE THEORY OF NEURAL NETWORKS.

Shun ichi Amari

The University of Tokyo

Research output: Contribution to conference › Paper › peer-review

4 Scopus citations

Abstract

The statistical neurodynamics of a simple autoassociative memory model is investigated. The topology and resolution of localized signal encoding in a neural field is discussed. It is shown that it is possible to predict neural characteristics and abilities of self-organizing neural fields by rigorous mathematical analysis.

Original language	English
Pages	iii/3-10
State	Published - 1987
Externally published	Yes

Cite this

@conference{449d36344dd44420bf225395dba64bf1,

title = "ON MATHEMATICAL METHODS IN THE THEORY OF NEURAL NETWORKS.",

abstract = "The statistical neurodynamics of a simple autoassociative memory model is investigated. The topology and resolution of localized signal encoding in a neural field is discussed. It is shown that it is possible to predict neural characteristics and abilities of self-organizing neural fields by rigorous mathematical analysis.",

author = "Amari, \{Shun ichi\}",

year = "1987",

language = "英語",

pages = "iii/3--10",

}

TY - CONF

T1 - ON MATHEMATICAL METHODS IN THE THEORY OF NEURAL NETWORKS.

AU - Amari, Shun ichi

PY - 1987

Y1 - 1987

N2 - The statistical neurodynamics of a simple autoassociative memory model is investigated. The topology and resolution of localized signal encoding in a neural field is discussed. It is shown that it is possible to predict neural characteristics and abilities of self-organizing neural fields by rigorous mathematical analysis.

AB - The statistical neurodynamics of a simple autoassociative memory model is investigated. The topology and resolution of localized signal encoding in a neural field is discussed. It is shown that it is possible to predict neural characteristics and abilities of self-organizing neural fields by rigorous mathematical analysis.

UR - https://www.scopus.com/pages/publications/0023548819

M3 - 論文

AN - SCOPUS:0023548819

SP - iii/3-10

ER -

ON MATHEMATICAL METHODS IN THE THEORY OF NEURAL NETWORKS.

Abstract

Other files and links

Fingerprint

Cite this