Title :
A sensitivity analysis algorithm for pruning feedforward neural networks
Author :
Engelbrech, AP ; Cloete, I.
Author_Institution :
Dept. of Comput. Sci., South Africa Univ., Pretoria, South Africa
Abstract :
A pruning algorithm, based on sensitivity analysis, is presented in this paper. We show that the sensitivity analysis technique efficiently prunes both input and hidden layers. Results of the application of the pruning algorithm to various N-bit parity problems agree with well-known published results
Keywords :
feedforward neural nets; learning (artificial intelligence); sensitivity analysis; feedforward neural networks; hidden layers; input layers; learning pattern; parity problems; pruning algorithm; sensitivity analysis; Africa; Computer networks; Computer science; Equations; Feedforward neural networks; Mathematical model; Neural networks; Sensitivity analysis;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549081
