Analytical approach based on information theory for neural network architecture

Serhat Seker

Analytical approach based on information theory for neural network architecture

Serhat Seker^*

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

In this study on the neural network architecture following its training period, with only one hidden layer and some constraints, the number of hidden nodes have been calculated by using the concepts of mean information quantity which was defined as an entropy and also, the importance of sigmoid function has been emphasized as the necessary condition of analytical approach used.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Publisher	Publ by IEEE
Pages	309-312
Number of pages	4
ISBN (Print)	0780314212, 9780780314214
Publication status	Published - 1993
Event	Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn Duration: 25 Oct 1993 → 29 Oct 1993

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	1

Conference

Conference	Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
City	Nagoya, Jpn
Period	25/10/93 → 29/10/93

Cite this

@inproceedings{376b32232f7a49c9b4e46d24dc075e98,

title = "Analytical approach based on information theory for neural network architecture",

abstract = "In this study on the neural network architecture following its training period, with only one hidden layer and some constraints, the number of hidden nodes have been calculated by using the concepts of mean information quantity which was defined as an entropy and also, the importance of sigmoid function has been emphasized as the necessary condition of analytical approach used.",

author = "Serhat Seker",

year = "1993",

language = "English",

isbn = "0780314212",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Publ by IEEE",

pages = "309--312",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) ; Conference date: 25-10-1993 Through 29-10-1993",

}

Seker, S 1993, Analytical approach based on information theory for neural network architecture. in Proceedings of the International Joint Conference on Neural Networks. Proceedings of the International Joint Conference on Neural Networks, vol. 1, Publ by IEEE, pp. 309-312, Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Jpn, 25/10/93.

Analytical approach based on information theory for neural network architecture. / Seker, Serhat.
Proceedings of the International Joint Conference on Neural Networks. Publ by IEEE, 1993. p. 309-312 (Proceedings of the International Joint Conference on Neural Networks; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Analytical approach based on information theory for neural network architecture

AU - Seker, Serhat

PY - 1993

Y1 - 1993

N2 - In this study on the neural network architecture following its training period, with only one hidden layer and some constraints, the number of hidden nodes have been calculated by using the concepts of mean information quantity which was defined as an entropy and also, the importance of sigmoid function has been emphasized as the necessary condition of analytical approach used.

AB - In this study on the neural network architecture following its training period, with only one hidden layer and some constraints, the number of hidden nodes have been calculated by using the concepts of mean information quantity which was defined as an entropy and also, the importance of sigmoid function has been emphasized as the necessary condition of analytical approach used.

UR - http://www.scopus.com/inward/record.url?scp=0027813422&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027813422

SN - 0780314212

SN - 9780780314214

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 309

EP - 312

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

T2 - Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)

Y2 - 25 October 1993 through 29 October 1993

ER -

Analytical approach based on information theory for neural network architecture

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this