Towards a generalization of decompositional approach of rule extraction from multilayer artificial neural network

摘要: The current development of knowledge discovery domain has pointed out a high number applications where the need explanation is at heart process. Using neural networks for those requires to be able provide set rules extracted from trained networks, that can help user comprehend learning literature reports two kinds rules: ‘if condition then conclusion’ (called if-then) and m conditions (also called MofN). We propose new method extract one intermediate structure generators list) which it possible both forms rules. generic representation gives possibility visualize each form multilayer artificial networks.