Knowledge Extraction from Radial Basis Function Networks and Multi-layer Perceptrons

Recently there has been a lot of interest in the extrac tion of symbolic rules from neural networks The work described in this paper is concerned with an evaluation and comparison of the accuracy and complexity of sym bolic rules extracted from radial basis function networks and multilayer perceptrons Here we examine the abil ity of rule extraction algorithms to extract meaningful rules that describe the overall performance of a particu lar network In addition the research also highlights the suitability of a specic neural network architecture for particular classication problems The research carried out on the extracted rule quality and complexity also has a direct bearing on the use of rule extraction algorithms for data mining and knowledge discovery

@InProceedings{MWM99, 
 	 author =  {McGarry, Ken and Wermter, Stefan and MacIntyre, J.},  
 	 title = {Knowledge Extraction from Radial Basis Function Networks and Multi-layer Perceptrons}, 
 	 booktitle = {Neural Networks, 1999. IJCNN' 99. International Joint Conference on Neural Networks},
 	 number = {},
 	 volume = {4},
 	 pages = {2494--2497},
 	 year = {1999},
 	 month = {Jul},
 	 publisher = {},
 	 doi = {10.1109/IJCNN.1999.833464}, 
 }