Adaptive regularizer for recursive neural network training algorithms

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...

Full description

Bibliographic Details
Main Author: Asirvadam, Vijanth Sagayan
Format: Conference or Workshop Item
Language:English
Published: 2008
Subjects:
Online Access:http://scholars.utp.edu.my/id/eprint/259/
http://scholars.utp.edu.my/id/eprint/259/1/paper.pdf
_version_ 1848658944499646464
author Asirvadam, Vijanth Sagayan
author_facet Asirvadam, Vijanth Sagayan
author_sort Asirvadam, Vijanth Sagayan
building UTP Institutional Repository
collection Online Access
description 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.
first_indexed 2025-11-13T07:22:35Z
format Conference or Workshop Item
id oai:scholars.utp.edu.my:259
institution Universiti Teknologi Petronas
institution_category Local University
language English
last_indexed 2025-11-13T07:22:35Z
publishDate 2008
recordtype eprints
repository_type Digital Repository
spelling oai:scholars.utp.edu.my:2592017-01-19T08:26:24Z http://scholars.utp.edu.my/id/eprint/259/ Adaptive regularizer for recursive neural network training algorithms Asirvadam, Vijanth Sagayan TK Electrical engineering. Electronics Nuclear engineering 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. 2008 Conference or Workshop Item NonPeerReviewed application/pdf en http://scholars.utp.edu.my/id/eprint/259/1/paper.pdf Asirvadam, Vijanth Sagayan (2008) Adaptive regularizer for recursive neural network training algorithms. In: 11th IEEE International Conference on Computational Science and Engineering, CSE Workshops 2008, 16 July 2008 through 18 July 2008, Sao Paulo, SP. http://www.scopus.com/inward/record.url?eid=2-s2.0-55849101672&partnerID=40&md5=269731419c26dfaff29ed744ee54d2b9
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Asirvadam, Vijanth Sagayan
Adaptive regularizer for recursive neural network training algorithms
title Adaptive regularizer for recursive neural network training algorithms
title_full Adaptive regularizer for recursive neural network training algorithms
title_fullStr Adaptive regularizer for recursive neural network training algorithms
title_full_unstemmed Adaptive regularizer for recursive neural network training algorithms
title_short Adaptive regularizer for recursive neural network training algorithms
title_sort adaptive regularizer for recursive neural network training algorithms
topic TK Electrical engineering. Electronics Nuclear engineering
url http://scholars.utp.edu.my/id/eprint/259/
http://scholars.utp.edu.my/id/eprint/259/
http://scholars.utp.edu.my/id/eprint/259/1/paper.pdf