Extracting Rules from Artificial Neural Networks with Distributed Representations

Although artificial neural networks have been applied in a variety of real-world scenarios with remarkable success, they have often been criticized for exhibiting a low degree of human comprehensibility. Techniques that compile compact sets of symbolic rules out of artificial neural networks offer a promising perspective to overcome this obvious deficiency of neural network representations. This paper presents an approach to the extraction of if-then rules from artificial neu(cid: 173) Its key mechanism is validity interval analysis, which is a generic ral networks. tool for extracting symbolic knowledge by propagating rule-like knowledge through Backpropagation-style neural networks. Empirical studies in a robot arm domain illus(cid: 173) trate the appropriateness of the proposed method for extracting rules from networks with real-valued and distributed representations.

Authors

• Sebastian Thrun Stanford University

Keywords

No keywords are indexed for this paper.