This paper suggests the "lnpUt-NetwOik-Training-0ulput-Extract~~Knowledge" framework to classify existing rule exlraction algorithms for feedloward neural networks. Based on the Suggested framework, we identify the major practices of existing algorithms as relying on the technique Of generate and test, which leads to exponential complexity, relying on specialized network structure and training ...

Over the last years, a number of studies on rule extraction from support vector machines (SVMs) have been introduced [1-5]. The research strategy in these projects is similar: to explore and develop algorithms for rule-extraction from SVMs based on the perception (or “view”) of the underlying SVM which is either explicitly or implicitly assumed within the rule extraction technique. In the conte...

A hybrid system using weightless neural networks (WNNs) and finite state automata is described in this paper. With the use of such a system, rules can be inserted and extracted into/from WNNs. The rule insertion and extraction problems are described with a detailed discussion of the advantages and disadvantages of the rule insertion and extraction algorithms proposed. The process of rule insert...

Though neural networks have achieved highest classification accuracy for many classification problems, the obtained results may not be interpretable as they are often considered as black box. To overcome this drawback researchers have developed many rule extraction algorithms. This paper has discussed on various rule extraction algorithms based on three different rule extraction approaches name...

Typically rule extraction is done for the purposes of human interpretation. However, there are other possible applications of rule extraction. One practical application is transfer learning, in which knowledge learned in one task is used to aid in learning a related task. The extracted rules, which explain the learned solution to the first task, can be considered advice on how to approach the s...

The aim of these enhancements is to improve the flexibility of the algorithms by decoupling the process of rule extraction that uses the concept lattice from the process of rule reduction that does not have to use it. With the added flexibility, an approach for parallel rule extraction and rule reduction is also presented.