03368nam a2200445 4500 20260817170959.0 030698 th eng .b10104628 AIT Thesis no. CS-92-10 Juneja, Hursh The back-propagation scheme in data classification : software and empirical guidelines Bangkok : Asian Institute of Technology, 1992 105 leaves Thesis ; no. CS-92-10 A thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering, School of Engineering and Technology Thesis (M.Eng.) - Asian Institute of Technology, 1992 The present study explores the applicability of Neural Networks to the problem of classification which is of great importance in many areas. For this purpose, a common neural network with back propagation aigorithm was used. First of all, a fully menu-driven and user friendly software package was developed to facilitate the application of this type of networks. It caters to numerical data input and is a fas~ high precision tool for neural network training. From a careful comparative study, it was found that for both normal and non-normal data, neural networks can result in better classification accuracy as comp{u00A5}ed to classical statistical methods, the latter being based on the assumption of an underlying data distribution. An attempt has also been made to formulate some guieielines to answer the questions regarding selection of a suitable learning rate and changing of thi ~ rate for faster convergence while training without any modifications to the training software. A third guideline has been proposed to decide the extent of training itself. All these can be achieved by careful examination of error and actual output curves of the training. Neural networks (Computer science) Information storage and retrieval systems Huynh, Ngoc Phien, Chairperson Sadananda, Ramakoti, Examination Committee Nagarur, Nagendra N., Examination Committee The Government Of Norway, Scholarship Donor Asian Institute of Technology. Thesis ; no. CS-92-10 Full-Text http://203.159.5.9/ait-thesis/detail.php?q=B16613 .b10104628 mnait v 250325 2 951012 m a v 4 mnait mnait mnarc mnarc 20 40 Barcode : 30050003100533 CREATED : 1994-05-16 RECORD # : i10115985 LPATRON : 0 LCHKIN : - # RENEWALS : 0 # OVERDUE : 0 IUSE3 : 0 TOT CHKOUT : 0 TOT RENEW : 0 Barcode : 30050003100541 CREATED : 1994-05-16 RECORD # : i10115997 LPATRON : 1013863 LCHKIN : 2000-07-10 # RENEWALS : 0 # OVERDUE : 0 IUSE3 : 0 TOT CHKOUT : 2 TOT RENEW : 0 Barcode : 30050120357420 CREATED : 2016-10-06 RECORD # : i13032483 LPATRON : 0 LCHKIN : - # RENEWALS : 0 # OVERDUE : 0 IUSE3 : 0 TOT CHKOUT : 0 TOT RENEW : 0 Barcode : 30050120919443 CREATED : 2019-11-25 RECORD # : i13233506 LPATRON : 0 LCHKIN : - # RENEWALS : 0 # OVERDUE : 0 IUSE3 : 0 TOT CHKOUT : 0 TOT RENEW : 0 10452 10452 0 0 0 0 MAIN MAIN mnait 2026-08-17 0 AIT Thesis no. CS-92-10 30050003100533 2026-08-17 17:09:59 1 2026-08-17 20 0 0 0 0 MAIN MAIN mnait 2026-08-17 0 AIT Thesis no. CS-92-10 30050003100541 2026-08-17 17:09:59 2 2026-08-17 20 0 0 0 0 MAIN MAIN mnarc 2026-08-17 0 AIT Thesis no. CS-92-10 30050120357420 2026-08-17 17:09:59 2026-08-17 40 0 0 0 0 MAIN MAIN mnarc 2026-08-17 50.00 0 AIT Thesis no. CS-92-10 30050120919443 2026-08-17 17:09:59 3 2026-08-17 20