000			03368nam a2200445 4500
005			20260817170959.0
008			030698 th eng
035			_a.b10104628
099		9	_aAIT Thesis no. CS-92-10
100	1		_aJuneja, Hursh
245	1	4	_aThe back-propagation scheme in data classification : _bsoftware and empirical guidelines
260			_aBangkok : _bAsian Institute of Technology, _c1992
300			_a105 leaves
490	1		_aThesis ; _vno. CS-92-10
500			_aA thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering, School of Engineering and Technology
502			_aThesis (M.Eng.) - Asian Institute of Technology, 1992
520			_aThe 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.
650		0	_aNeural networks (Computer science)
650		0	_aInformation storage and retrieval systems
700	1		_aHuynh, Ngoc Phien, _eChairperson
700	1		_aSadananda, Ramakoti, _eExamination Committee
700	1		_aNagarur, Nagendra N., _eExamination Committee
710	2		_aThe Government Of Norway, _eScholarship Donor
810	2		_aAsian Institute of Technology. _tThesis ; _vno. CS-92-10
856			_3Full-Text _uhttp://203.159.5.9/ait-thesis/detail.php?q=B16613
907			_a.b10104628 _bmnait _cv
902			_a250325
998			_b2 _c951012 _dm _ea _fv _g4
945			_lmnait
945			_lmnait
945			_lmnarc
945			_lmnarc
942			_c20
942			_c40
909			_aBarcode : 30050003100533 _bCREATED : 1994-05-16 _cRECORD # : i10115985 _dLPATRON : 0 _eLCHKIN : - _f# RENEWALS : 0 _g# OVERDUE : 0 _hIUSE3 : 0 _iTOT CHKOUT : 0 _jTOT RENEW : 0
909			_aBarcode : 30050003100541 _bCREATED : 1994-05-16 _cRECORD # : i10115997 _dLPATRON : 1013863 _eLCHKIN : 2000-07-10 _f# RENEWALS : 0 _g# OVERDUE : 0 _hIUSE3 : 0 _iTOT CHKOUT : 2 _jTOT RENEW : 0
909			_aBarcode : 30050120357420 _bCREATED : 2016-10-06 _cRECORD # : i13032483 _dLPATRON : 0 _eLCHKIN : - _f# RENEWALS : 0 _g# OVERDUE : 0 _hIUSE3 : 0 _iTOT CHKOUT : 0 _jTOT RENEW : 0
909			_aBarcode : 30050120919443 _bCREATED : 2019-11-25 _cRECORD # : i13233506 _dLPATRON : 0 _eLCHKIN : - _f# RENEWALS : 0 _g# OVERDUE : 0 _hIUSE3 : 0 _iTOT CHKOUT : 0 _jTOT RENEW : 0
999			_c10452 _d10452