Title :
Pattern recognition with block-based neural networks
Author :
Moon, Sang-Woo ; Kong, Seong-Gon
Author_Institution :
Dept. of Electr. Eng., Soongsil Univ., Seoul, South Korea
fDate :
6/24/1905 12:00:00 AM
Abstract :
This paper presents block-based neural net works (BbNNs) for pattern classification. The BbNN achieves two goals: simultaneous optimization of network structure/weights; and implementation using reconfigurable digital hardware. The BbNN, in a 2-D array of basic blocks with four variable input/output nodes, successfully solve pattern classification problems. Internal structure is optimized using the GA with 2-D encoding scheme
Keywords :
neural nets; optimisation; pattern recognition; 2D array; 2D encoding scheme; BbNN; GA; block-based neural networks; genetic algorithm; internal structure optimization; network structure; network weights; pattern classification; pattern recognition; reconfigurable digital hardware; simultaneous optimization; Artificial neural networks; Binary codes; Encoding; Evolutionary computation; Genetic algorithms; Neural network hardware; Neural networks; Pattern classification; Pattern recognition; Programmable logic arrays;
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.2002.1005610
