Macot, Luc (1998) New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays. PhD thesis, Concordia University.
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.
|Divisions:||Concordia University > Faculty of Arts and Science > Physics|
|Item Type:||Thesis (PhD)|
|Pagination:||xvii, 255 leaves : ill. ; 29 cm.|
|Degree Name:||Theses (Ph.D.)|
|Thesis Supervisor(s):||Frank, Barry|
|Deposited By:||Concordia University Libraries|
|Deposited On:||27 Aug 2009 17:12|
|Last Modified:||08 Dec 2010 15:14|
Repository Staff Only: item control page