eprintid: 423
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/04/23
datestamp: 2023-11-09 15:16:03
lastmod: 2023-11-09 15:16:03
status_changed: 2023-11-09 15:14:31
type: conference_item
metadata_visibility: show
creators_name: Asirvadam, V.S.
title: Adaptive regularizer for recursive neural network training algorithms
ispublished: pub
keywords: Neural networks; Recursive functions; Technical presentations, Levenberg-marquardt; Multilayer perceptions; Novel applications; Parameter corrections; Recursive neural networks, Adaptive algorithms
note: cited By 6; Conference of 11th IEEE International Conference on Computational Science and Engineering, CSE Workshops 2008 ; Conference Date: 16 July 2008 Through 18 July 2008; Conference Code:73977
abstract: Adaptive Marquardt parameter correction techniques are tested for recursive Levenberg-Marquardt (RLM) and proposed novel application on decomposed recursive Levenberg Marquardt (DRLM) algorithms. The adaptive Marquardt correction is based on recursive moving-window residual. Experiment results show superior convergence using decomposed approach and a slight improvement in performance by adopting the adaptive Marquardt correction on a fixed size multilayer perceptions (MLP) network. © 2008 IEEE.
date: 2008
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-55849101672&doi=10.1109%2fCSEW.2008.55&partnerID=40&md5=d4333cf55459294e676abc6bc354cff7
id_number: 10.1109/CSEW.2008.55
full_text_status: none
publication: Proceedings of the 11th IEEE International Conference on Computational Science and Engineering, CSE Workshops 2008
place_of_pub: Sao Paulo, SP
pagerange: 89-94
refereed: TRUE
isbn: 9780769532578
citation:   Asirvadam, V.S.  (2008) Adaptive regularizer for recursive neural network training algorithms.  In: UNSPECIFIED.