Adaptive regularizer for recursive neural network training algorithms

• Main Author: Asirvadam, Vijanth Sagayan
• Format: Conference or Workshop Item
• Published: 2008
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utp.edu.my/259/1/paper.pdf; http://www.scopus.com/inward/record.url?eid=2-s2.0-55849101672&partnerID=40&md5=269731419c26dfaff29ed744ee54d2b9; http://eprints.utp.edu.my/259/

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...