Growing network that optimizes between undertraining and overtraining

Goutam Chakraborty; Mitsuru Murakami; Norio Shiratori; Shoichi Noguchi

Growing network that optimizes between undertraining and overtraining

Goutam Chakraborty^*, Mitsuru Murakami, Norio Shiratori, Shoichi Noguchi

^*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

Feedforward neural network classifier trained with a finite set of available sample tries to estimate properly the different class boundaries in the input feature space. This enables the network to classify unknown new samples with some confidence. A new method for ascertaining proper network size for maximizing generalization as well as correct classification is proposed. An algorithm is also proposed to grow the network to that size.

Original language	English
Title of host publication	IEEE International Conference on Neural Networks - Conference Proceedings
Place of Publication	Piscataway, NJ, United States
Publisher	IEEE
Pages	1116-1120
Number of pages	5
Volume	2
Publication status	Published - 1995
Event	Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust Duration: 1995 Nov 27 → 1995 Dec 1

Other

Other	Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
City	Perth, Aust
Period	95/11/27 → 95/12/1

ASJC Scopus subject areas

Software

Cite this

Chakraborty, G, Murakami, M, Shiratori, N & Noguchi, S 1995, Growing network that optimizes between undertraining and overtraining. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 2, IEEE, Piscataway, NJ, United States, pp. 1116-1120, Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 95/11/27.

@inproceedings{45155ec371db4b68b39c50816f3b360a,

title = "Growing network that optimizes between undertraining and overtraining",

abstract = "Feedforward neural network classifier trained with a finite set of available sample tries to estimate properly the different class boundaries in the input feature space. This enables the network to classify unknown new samples with some confidence. A new method for ascertaining proper network size for maximizing generalization as well as correct classification is proposed. An algorithm is also proposed to grow the network to that size.",

author = "Goutam Chakraborty and Mitsuru Murakami and Norio Shiratori and Shoichi Noguchi",

year = "1995",

language = "English",

volume = "2",

pages = "1116--1120",

booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

publisher = "IEEE",

note = "Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) ; Conference date: 27-11-1995 Through 01-12-1995",

}

TY - GEN

T1 - Growing network that optimizes between undertraining and overtraining

AU - Chakraborty, Goutam

AU - Murakami, Mitsuru

AU - Shiratori, Norio

AU - Noguchi, Shoichi

PY - 1995

Y1 - 1995

N2 - Feedforward neural network classifier trained with a finite set of available sample tries to estimate properly the different class boundaries in the input feature space. This enables the network to classify unknown new samples with some confidence. A new method for ascertaining proper network size for maximizing generalization as well as correct classification is proposed. An algorithm is also proposed to grow the network to that size.

AB - Feedforward neural network classifier trained with a finite set of available sample tries to estimate properly the different class boundaries in the input feature space. This enables the network to classify unknown new samples with some confidence. A new method for ascertaining proper network size for maximizing generalization as well as correct classification is proposed. An algorithm is also proposed to grow the network to that size.

UR - http://www.scopus.com/inward/record.url?scp=0029489320&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029489320&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029489320

VL - 2

SP - 1116

EP - 1120

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

CY - Piscataway, NJ, United States

T2 - Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)

Y2 - 27 November 1995 through 1 December 1995

ER -

Growing network that optimizes between undertraining and overtraining

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this