Title :
Graph isomorphisms effect on structure optimization of neural networks
Author :
Igel, Christian ; Stagge, Peter
Author_Institution :
Inst. fur Neuroinformatik, Ruhr-Univ., Bochum, Germany
fDate :
6/24/1905 12:00:00 AM
Abstract :
Concepts from the graph theory and molecular evolution are proposed for analyzing effects of redundancy induced by graph isomorphisms on the structure optimization of neural networks. It is demonstrated that a graph database that considers isomorphisms can drastically reduce the number of evaluations in an evolutionary structure optimization process
Keywords :
feedforward neural nets; genetic algorithms; graph theory; multilayer perceptrons; network topology; probability; redundancy; evolutionary algorithms; evolutionary structure optimization; feedforward neural networks; graph isomorphisms; graph theory; molecular evolution; multilayer perceptron; neural networks; probability; topology; Databases; Evolutionary computation; Feedforward neural networks; Graph theory; Labeling; Multilayer perceptrons; Network topology; Neural networks; Neurons; Optimization methods;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005459
