DocumentCode :
1682540
Title :
Architecture selection for neural networks
Author :
Karampiperis, Pythagoras ; Manouselis, Nikos ; Trafalis, Theodore B.
Author_Institution :
Dept. of Electron. & Comput. Eng., Tech. Univ. of Crete, Greece
Volume :
2
fYear :
2002
fDate :
6/24/1905 12:00:00 AM
Firstpage :
1115
Lastpage :
1119
Abstract :
Researchers worldwide converge into the fact that the exhaustive search over the space of network architectures is computationally infeasible even for networks of modest size. The use of heuristic strategies that dramatically reduce the search complexity is a common technique. These heuristic approaches employ directed search algorithms, such as selection of the number of nodes via sequential network construction (SNC), pruning inputs and weights via sensitivity based pruning (SBP) and optimal brain damage (OBD). The main disadvantage of the particular techniques is the production of one hidden layer only perceptrons and not a multiplayer network. As a consequence we cannot ensure that the resulted network will produce "optimal" results. This paper investigates the use of other heuristic strategies that produce multiplayer perceptrons. We propose three algorithms for the construction of networks and compare them with the classic approaches. Simulation results show that these methods lead to "near-optimal" network structures by engaging error-related information
Keywords :
computational complexity; multilayer perceptrons; neural nets; search problems; architecture selection; directed search algorithms; error-related information; exhaustive search; heuristic strategies; multiplayer perceptrons; network architectures; neural networks; optimal brain damage; pruning inputs; search complexity; sensitivity based pruning; sequential network construction; simulation results; Biological neural networks; Computer architecture; Computer networks; Heuristic algorithms; Multilayer perceptrons; Neural networks; Neurons; Production engineering; Space technology; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
ISSN :
1098-7576
Print_ISBN :
0-7803-7278-6
Type :
conf
DOI :
10.1109/IJCNN.2002.1007650
Filename :
1007650
Link To Document :
بازگشت