NEURAL-NETWORK FITS TO NEUTRON-INDUCED REACTIONS USING WEIGHTED LEAST-MEAN-SQUARES

Authors
DUBEY BP KATARIA SK MOHANTY AK
Citation
Bp. Dubey et al., NEURAL-NETWORK FITS TO NEUTRON-INDUCED REACTIONS USING WEIGHTED LEAST-MEAN-SQUARES, Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment, 397(2-3), 1997, pp. 426-439
Citations number
10
Categorie Soggetti
Nuclear Sciences & Tecnology","Physics, Particles & Fields","Instument & Instrumentation",Spectroscopy
Journal title
Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment → ACNP
ISSN journal
01689002
Volume
397
Issue
2-3
Year of publication
1997
Pages
426 - 439
Database
ISI
SICI code
0168-9002(1997)397:2-3<426:NFTNRU>2.0.ZU;2-B
Abstract
A new error function based on weighted least-mean-square analysis is s uggested for use in a bask-propagation algorithm in neural networks. T he standard back-propagation algorithm has been revised to minimize th e sum of the weighted residual error squared. This method has been app lied to obtain the cross-section For 14.6 MeV neutron induced (n, p) a nd (n, alpha) reactions in the mass region 40 < A < 240. In comparison to the normal back-propagation algorithm based on simple least mean s quare error estimation? the proposed method has better estimation powe r particularly in a situation when the targeted outputs have large var iations in experimental errors.