Title :
Optimization of input size for neural networks
Author :
Lee, Bongkyu ; Cho, Seongwon
Author_Institution :
Dept. of Comput. Sci., Cheju Univ., South Korea
Abstract :
A selection scheme to determine the optimal number of input nodes for neural networks is presented. The proposed scheme selects only the features contributing to correct classification. Experimental results indicates that the proposed selection scheme improves the speed of neural networks
Keywords :
neural nets; optimisation; pattern classification; input nodes; input size; neural networks; Computer science; Equations; Intelligent networks; Neural networks; Ordinary magnetoresistance; Pattern recognition; Radiofrequency interference;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.687151