eprintid: 980 rev_number: 2 eprint_status: archive userid: 1 dir: disk0/00/00/09/80 datestamp: 2023-11-09 15:49:08 lastmod: 2023-11-09 15:49:08 status_changed: 2023-11-09 15:38:48 type: conference_item metadata_visibility: show creators_name: Izzeldin, H. creators_name: Asirvadam, V.S. creators_name: Saad, N. title: Enhanced conjugate gradient methods for training MLP-networks ispublished: pub keywords: Bench-mark problems; Broyden; Computational time; Conjugate gradient; Conjugate gradient algorithms; Memory usage; Multilayer perceptron neural networks; Offline learning; Prediction errors; Training algorithms, Algorithms; Conjugate gradient method; Engineering research; Innovation; Network architecture, Neural networks note: cited By 4; Conference of 2010 8th IEEE Student Conference on Research and Development - Engineering: Innovation and Beyond, SCOReD 2010 ; Conference Date: 13 December 2010 Through 14 December 2010; Conference Code:83885 abstract: The paper investigates the enhancement in various conjugate gradient training algorithms applied to a multilayer perceptron (MLP) neural network architecture. The paper investigates seven different conjugate gradient algorithms proposed by different researchers from 1952-2005, the classical batch back propagation, full-memory and memory-less BFGS (Broyden, Fletcher, Goldfarb and Shanno) algorithms. These algorithms are tested in predicting fluid height in two different control tank benchmark problems. Simulations results show that Full-Memory BFGS has overall better performance or less prediction error however it has higher memory usage and longer computational time conjugate gradients. ©2010 IEEE. date: 2010 official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-79951986009&doi=10.1109%2fSCORED.2010.5703989&partnerID=40&md5=abec87933aec16425408303635d9a44b id_number: 10.1109/SCORED.2010.5703989 full_text_status: none publication: Proceeding, 2010 IEEE Student Conference on Research and Development - Engineering: Innovation and Beyond, SCOReD 2010 place_of_pub: Kuala Lumpur pagerange: 139-143 refereed: TRUE isbn: 9781424486489 citation: Izzeldin, H. and Asirvadam, V.S. and Saad, N. (2010) Enhanced conjugate gradient methods for training MLP-networks. In: UNSPECIFIED.