J
Jude W. Shavlik
Researcher at University of Wisconsin-Madison
Publications - 211
Citations - 11619
Jude W. Shavlik is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Artificial neural network & Statistical relational learning. The author has an hindex of 53, co-authored 211 publications receiving 11095 citations. Previous affiliations of Jude W. Shavlik include University of Illinois at Urbana–Champaign.
Papers
More filters
Journal ArticleDOI
Knowledge-based artificial neural networks
TL;DR: These tests show that the networks created by KBANN generalize better than a wide variety of learning systems, as well as several techniques proposed by biologists.
Proceedings Article
Extracting Tree-Structured Representations of Trained Networks
Mark Craven,Jude W. Shavlik +1 more
TL;DR: This work presents a novel algorithm, TREPAN, for extracting comprehensible, symbolic representations from trained neural networks, which is general in its applicability and scales well to large networks and problems with high-dimensional input spaces.
Journal ArticleDOI
Extracting Refined Rules from Knowledge-Based Neural Networks
TL;DR: This article proposes and empirically evaluates a method for the final, and possibly most difficult, step of the refinement of existing knowledge and demonstrates that neural networks can be used to effectively refine symbolic knowledge.
Proceedings Article
Refinement of approximate domain theories by knowledge-based neural networks
TL;DR: The KBANN system relaxes this constraint through the use of empirical learning methods to refine approximately correct knowledge, used to determine the structure of an artificial neural network and the weights on its links, thereby making the knowledge accessible for modification by neural learning.
Proceedings Article
Generating Accurate and Diverse Members of a Neural-Network Ensemble
David W. Opitz,Jude W. Shavlik +1 more
TL;DR: A technique called ADDEMUP is presented that uses genetic algorithms to directly search for an accurate and diverse set of trained networks and is able to effectively incorporate prior knowledge, if available, to improve the quality of its ensemble.