Homepage
Research
Students
Courses
Robots
Papers
Videos
Press
Talks
Faq
CV
Lab
Travel
Contact
Personal
Links


Extracting Rules from Artificial Neural Networks with Distributed Representations

Sebastian Thrun

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 neural networks. Its key mechanism is validity interval analysis, which is a generic tool for extracting symbolic knowledge by propagating rule-like knowledge through Backpropagation-style neural networks. Empirical studies in a robot arm domain illustrate the appropriateness of the proposed method for extracting rules from networks with real-valued and distributed representations.

Click here to obtain the full paper (91817 bytes).

@INPROCEEDINGS{Thrun95b,
  AUTHOR         = {S. Thrun},
  YEAR           = {1995},
  TITLE          = {Extracting Rules from Artificial Neural Networks with Distributed Representations},
  BOOKTITLE      = {Advances in Neural Information Processing Systems 
                    (NIPS) 7},
  EDITOR         = {G. Tesauro and D. Touretzky and T. Leen},
  PUBLISHER      = {MIT Press},
  ADDRESS        = {Cambridge, MA}
}