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

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method'. Together they form a unique fingerprint.

Cite this