Stabilization of sequential learning neural network in sonar target classification via a novel approach

Lim, , WS and Rao, , MVC (2005) Stabilization of sequential learning neural network in sonar target classification via a novel approach. NEURAL NETWORK WORLD, 15 I (2). pp. 111-127. ISSN 1210-0552

Full text not available from this repository.

Abstract

In this paper, the processing of sonar signals has been carried out using a Minimal Resource Allocation Network (MRAN) in identification of commonly encountered features in indoor environments. The stability-plasticity behaviors of the network have been investigated. From previous observations, the experimental results show that MRAN possesses lower network complexity but experiences higher plasticity, and is unstable. A novel approach is proposed to solve these problems in MRAN and has also been experimentally proven that the network generalizes faster at a lower number of neurons (nodes) compared to the original MRAN. This new approach has been applied as a preprocessing tool to equip the network with certain information about the data to be used in training the network later. With this initial 'guidance', the network predicts extremely well in both sequential and random learning.

Item Type: Article
Subjects: Q Science > QA Mathematics > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 24 Aug 2011 02:53
Last Modified: 24 Aug 2011 02:53
URI: http://shdl.mmu.edu.my/id/eprint/2321

Actions (login required)

View Item View Item