Three techniques for extracting rules from feedforward networks

Hybrid intelligent systems that combine knowledge based and artiicial neural network systems typically have four phases involving domain knowledge representation, mapping into connectionist network, network training, and rule extraction respectively. The nal phase is important because it can provide a trained connectionist architecture with explanation power and validate its output decisions. Moreover, it can be used to reene and maintain the initial knowledge acquired from domain experts. In this paper, we introduce three new rule extraction techniques. The rst technique extracts a set of binary rules from any neural network regardless of its kind (MLP, RBF etc.,). The second technique extracts partial rules that represent the most important embedded knowledge in a trained MLP. The delity of the second technique is adjustable to the desired level of knowledge extraction. The third technique is a universal and comprehensive approach that extracts almost all embedded knowledge in a trained artiicial neural network and represents it in a rule base format. Experimental results of implementing these three rule extraction techniques are presented.