@inproceedings{scholars423, pages = {89--94}, journal = {Proceedings of the 11th IEEE International Conference on Computational Science and Engineering, CSE Workshops 2008}, address = {Sao Paulo, SP}, title = {Adaptive regularizer for recursive neural network training algorithms}, year = {2008}, doi = {10.1109/CSEW.2008.55}, 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}, author = {Asirvadam, V. S.}, isbn = {9780769532578}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-55849101672&doi=10.1109\%2fCSEW.2008.55&partnerID=40&md5=d4333cf55459294e676abc6bc354cff7}, keywords = {Neural networks; Recursive functions; Technical presentations, Levenberg-marquardt; Multilayer perceptions; Novel applications; Parameter corrections; Recursive neural networks, Adaptive algorithms}, 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. {\^A}{\copyright} 2008 IEEE.} }