Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method

Siddhaling Urolagin, K. V. Prema, R. Jayakrishna, N. V.Subba Reddy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The Artificial Neural Network (ANN) with small size may not solve the problem while the network with large size will suffer from poor generalization. The pruning methods are approaches for finding appropriate size of the network by eliminating few parameters from the network. The sensitivity based pruning will determine sensitivity of the network error for removal of a parameter and eliminate parameters with least sensitivity. In this research a sensitivity based pruning method is integrated with multilayer feed-forward ANN and applied on MNIST handwritten numeral recognition. An analysis of effect of pruning on the network is compared with performance of a network without pruning. It is observed that the network integrated with pruning method show better generalization ability than a network without pruning method being incorporated.

Original languageEnglish
Title of host publicationAdvances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers
Pages68-74
Number of pages7
DOIs
Publication statusPublished - 01-12-2012
Event3rd International Conference on Advances in Communication, Network, and Computing, CNC 2012 - Chennai, India
Duration: 24-02-201225-02-2012

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering
Volume108 LNICST
ISSN (Print)1867-8211

Conference

Conference3rd International Conference on Advances in Communication, Network, and Computing, CNC 2012
CountryIndia
CityChennai
Period24-02-1225-02-12

Fingerprint

Multilayers
Neural networks

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Urolagin, S., Prema, K. V., Jayakrishna, R., & Reddy, N. V. S. (2012). Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method. In Advances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers (pp. 68-74). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering; Vol. 108 LNICST). https://doi.org/10.1007/978-3-642-35615-5_10
Urolagin, Siddhaling ; Prema, K. V. ; Jayakrishna, R. ; Reddy, N. V.Subba. / Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method. Advances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers. 2012. pp. 68-74 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering).
@inproceedings{57c038bdff0b47639dfb695bdcf2fb3d,
title = "Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method",
abstract = "The Artificial Neural Network (ANN) with small size may not solve the problem while the network with large size will suffer from poor generalization. The pruning methods are approaches for finding appropriate size of the network by eliminating few parameters from the network. The sensitivity based pruning will determine sensitivity of the network error for removal of a parameter and eliminate parameters with least sensitivity. In this research a sensitivity based pruning method is integrated with multilayer feed-forward ANN and applied on MNIST handwritten numeral recognition. An analysis of effect of pruning on the network is compared with performance of a network without pruning. It is observed that the network integrated with pruning method show better generalization ability than a network without pruning method being incorporated.",
author = "Siddhaling Urolagin and Prema, {K. V.} and R. Jayakrishna and Reddy, {N. V.Subba}",
year = "2012",
month = "12",
day = "1",
doi = "10.1007/978-3-642-35615-5_10",
language = "English",
isbn = "9783642356148",
series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering",
pages = "68--74",
booktitle = "Advances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers",

}

Urolagin, S, Prema, KV, Jayakrishna, R & Reddy, NVS 2012, Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method. in Advances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, vol. 108 LNICST, pp. 68-74, 3rd International Conference on Advances in Communication, Network, and Computing, CNC 2012, Chennai, India, 24-02-12. https://doi.org/10.1007/978-3-642-35615-5_10

Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method. / Urolagin, Siddhaling; Prema, K. V.; Jayakrishna, R.; Reddy, N. V.Subba.

Advances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers. 2012. p. 68-74 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering; Vol. 108 LNICST).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method

AU - Urolagin, Siddhaling

AU - Prema, K. V.

AU - Jayakrishna, R.

AU - Reddy, N. V.Subba

PY - 2012/12/1

Y1 - 2012/12/1

N2 - The Artificial Neural Network (ANN) with small size may not solve the problem while the network with large size will suffer from poor generalization. The pruning methods are approaches for finding appropriate size of the network by eliminating few parameters from the network. The sensitivity based pruning will determine sensitivity of the network error for removal of a parameter and eliminate parameters with least sensitivity. In this research a sensitivity based pruning method is integrated with multilayer feed-forward ANN and applied on MNIST handwritten numeral recognition. An analysis of effect of pruning on the network is compared with performance of a network without pruning. It is observed that the network integrated with pruning method show better generalization ability than a network without pruning method being incorporated.

AB - The Artificial Neural Network (ANN) with small size may not solve the problem while the network with large size will suffer from poor generalization. The pruning methods are approaches for finding appropriate size of the network by eliminating few parameters from the network. The sensitivity based pruning will determine sensitivity of the network error for removal of a parameter and eliminate parameters with least sensitivity. In this research a sensitivity based pruning method is integrated with multilayer feed-forward ANN and applied on MNIST handwritten numeral recognition. An analysis of effect of pruning on the network is compared with performance of a network without pruning. It is observed that the network integrated with pruning method show better generalization ability than a network without pruning method being incorporated.

UR - http://www.scopus.com/inward/record.url?scp=84873946051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873946051&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-35615-5_10

DO - 10.1007/978-3-642-35615-5_10

M3 - Conference contribution

SN - 9783642356148

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering

SP - 68

EP - 74

BT - Advances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers

ER -

Urolagin S, Prema KV, Jayakrishna R, Reddy NVS. Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method. In Advances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers. 2012. p. 68-74. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering). https://doi.org/10.1007/978-3-642-35615-5_10