Adaptive regularizer for recursive neural network training algorithms

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.

[thumbnail of Adaptive regularizer for recursive neural network training algorithms] PDF (Adaptive regularizer for recursive neural network training algorithms)
paper.pdf - Published Version
Restricted to Registered users only

Download (12kB) | Request a copy
Official URL: http://www.scopus.com/inward/record.url?eid=2-s2.0...

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.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Neural networks; Recursive functions; Technical presentations; Levenberg-marquardt; Multilayer perceptions; Novel applications; Parameter corrections; Recursive neural networks; Adaptive algorithms
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Departments / MOR / COE: Departments > Electrical & Electronic Engineering
Depositing User: Dr Vijanth Sagayan Asirvadam
Date Deposited: 02 Mar 2010 01:18
Last Modified: 19 Jan 2017 08:26
URI: http://scholar.utp.edu.my/id/eprint/259

Actions (login required)

View Item
View Item