DocumentCode
3782591
Title
Comparative analysis of different learning algorithms on a common neural network structure
Author
C. Moraga;A. Gasch
Author_Institution
Dept. of Comput. Sci., Comput. Eng. & Comput. Educ., Dortmund Univ., Germany
fYear
1999
Firstpage
19
Lastpage
24
Abstract
A feedforward neural network with one hidden layer and full connection is analyzed from several points of view and trained with different algorithms. A comparative performance analysis shows marginal differences supporting the conclusion that the network architecture has a stronger influence upon the performance than the training algorithm.
Keywords
"Algorithm design and analysis","Neural networks","Computer networks","Multi-layer neural network","Feedforward neural networks","Computer science","Computer science education","Read only memory","Benchmark testing","Electrical capacitance tomography"
Publisher
ieee
Conference_Titel
Computer Science Society, 1999. Proceedings. SCCC ´99. XIX International Conference of the Chilean
ISSN
1522-4902
Print_ISBN
0-7695-0296-2
Type
conf
DOI
10.1109/SCCC.1999.810149
Filename
810149
Link To Document