An Overview of Research at Wisconsin on Knowledge-Based Neural Networks

Recent research at the University of Wisconsin on knowledge-based neural networks is surveyed. This work has focused on (a) using symbolically represented background knowledge to improve neural-network learning and (b) extracting comprehensible symbolic representations from trained networks. Important open issues are discussed.

[1]  David W. Opitz,et al.  An anytime approach to connectionist theory refinement - refining the topologies of knowledge-based neural networks , 1996, Technical Report / University of Wisconsin, Madison / Computer Sciences Department.

[2]  Jude W. Shavlik,et al.  Using Sampling and Queries to Extract Rules from Trained Neural Networks , 1994, ICML.

[3]  Jude Shavlik,et al.  An Approach to Combining Explanation-based and Neural Learning Algorithms , 1989 .

[4]  David W. Opitz,et al.  Generating Accurate and Diverse Members of a Neural-Network Ensemble , 1995, NIPS.

[5]  David W. Opitz,et al.  Dynamically adding symbolically meaningful nodes to knowledge-based neural networks , 1995, Knowl. Based Syst..

[6]  Jude W. Shavlik,et al.  Incorporating Advice into Agents that Learn from Reinforcements , 1994, AAAI.

[7]  Richard Maclin.  Learning From Instruction And Experience: Methods For Incorporating Procedural Domain Theories Into , 1995 .

[8]  Jude W. Shavlik,et al.  Learning Symbolic Rules Using Artificial Neural Networks , 1993, ICML.

[9]  Jude W. Shavlik,et al.  Creating Advice-Taking Reinforcement Learners , 1998, Machine Learning.

[10]  David W. Opitz,et al.  Heuristically Expanding Knowledge-Based Neural Networks , 1993, IJCAI.

[11]  Jude W. Shavlik,et al.  in Advances in Neural Information Processing , 1996 .

[12]  J. Shavlik,et al.  Extracting Reened Rules from Knowledge-based Neural Networks Keywords: Theory Reenement Integrated Learning Representational Shift Rule Extraction from Neural Networks , 1992 .

[13]  David W. Opitz,et al.  Using Genetic Search to Refine Knowledge-based Neural Networks , 1994, ICML.

[14]  Geoffrey G. Towell,et al.  Symbolic knowledge and neural networks: insertion, refinement and extraction , 1992 .