Title :
A new pruning algorithm for neural network dimension analysis
Author :
Sabo, Devin ; Yu, Xiao-Hua
Author_Institution :
Lockheed Martin Corp., Sunnyvale, CA
Abstract :
The choice of network dimension is a fundamental issue in neural network applications. An optimal neural network topology not only reduces the computational complexity, but also improves its generalization capacity. In this research, a new pruning algorithm based on cross validation and sensitivity analysis is developed and compared with three existing pruning algorithms on various pattern classification problems. Computer simulation results show the network size can be significantly reduced using this new algorithm while the neural network still maintains satisfactory generalization accuracy.
Keywords :
computational complexity; generalisation (artificial intelligence); neural nets; pattern classification; sensitivity analysis; computational complexity; cross validation; generalization capacity; network dimension; neural network dimension analysis; optimal neural network topology; pattern classification; pruning algorithm; sensitivity analysis; Algorithm design and analysis; Neural networks;
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2008.4634268