New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays

New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays

A new neural network learning algorithm, called the Umbrella Algorithm, is developed and analysed. Its generalization, which does not exhibit over-specialisation, is observed in the EXOR problem and in an artificial data discrimination (Toy Data) problem. The learning time is found to be about 1/15...

Full description

Bibliographic Details
Main Author: Macot, Luc
Format: Others
Published: 1998
Online Access:http://spectrum.library.concordia.ca/471/1/NQ40302.pdf
Macot, Luc <http://spectrum.library.concordia.ca/view/creators/Macot=3ALuc=3A=3A.html> (1998) New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays. PhD thesis, Concordia University.
id ndltd-LACETR-oai-collectionscanada.gc.ca-QMG.471
record_format oai_dc
spelling ndltd-LACETR-oai-collectionscanada.gc.ca-QMG.4712013-10-22T03:40:20Z New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays Macot, Luc A new neural network learning algorithm, called the Umbrella Algorithm, is developed and analysed. Its generalization, which does not exhibit over-specialisation, is observed in the EXOR problem and in an artificial data discrimination (Toy Data) problem. The learning time is found to be about 1/15 of backpropagation learning time for the parity problem. The algorithm is applied to cosmic high energy gamma ray detection and is further used for determining the spectral index of the Markarian 421 source. 1998 Thesis NonPeerReviewed application/pdf http://spectrum.library.concordia.ca/471/1/NQ40302.pdf Macot, Luc <http://spectrum.library.concordia.ca/view/creators/Macot=3ALuc=3A=3A.html> (1998) New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays. PhD thesis, Concordia University. http://spectrum.library.concordia.ca/471/
collection NDLTD
format Others
sources NDLTD
description A new neural network learning algorithm, called the Umbrella Algorithm, is developed and analysed. Its generalization, which does not exhibit over-specialisation, is observed in the EXOR problem and in an artificial data discrimination (Toy Data) problem. The learning time is found to be about 1/15 of backpropagation learning time for the parity problem. The algorithm is applied to cosmic high energy gamma ray detection and is further used for determining the spectral index of the Markarian 421 source.
author Macot, Luc
spellingShingle Macot, Luc
New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays
author_facet Macot, Luc
author_sort Macot, Luc
title New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays
title_short New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays
title_full New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays
title_fullStr New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays
title_full_unstemmed New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays
title_sort new algorithm for neural network data discrimination applied to markarian 421 high energy gamma rays
publishDate 1998
url http://spectrum.library.concordia.ca/471/1/NQ40302.pdf
Macot, Luc <http://spectrum.library.concordia.ca/view/creators/Macot=3ALuc=3A=3A.html> (1998) New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays. PhD thesis, Concordia University.
work_keys_str_mv AT macotluc newalgorithmforneuralnetworkdatadiscriminationappliedtomarkarian421highenergygammarays
_version_ 1716605368946130944

Similar Items