Experiments on multistrategy learning by meta-learning
CIKM '93 Proceedings of the second international conference on Information and knowledge management
ACM SIGART Bulletin
On the Accuracy of Meta-learning for Scalable Data Mining
Journal of Intelligent Information Systems
PAL: A Pattern-Based First-Order Inductive System
Machine Learning - special issue on inductive logic programming
Representational effects in a simple classifier system
SAC '94 Proceedings of the 1994 ACM symposium on Applied computing
Reorganizing Knowledge to Improve Performance
IEEE Transactions on Knowledge and Data Engineering
Machines that learn to play games
Discovery of empirical theories based on the measurement theory
Minds and Machines - Machine learning as experimental philosophy of science
Connectionist theory refinement: genetically searching the space of network topologies
Journal of Artificial Intelligence Research
Rerepresenting and restructuring domain theories: a constructive induction approach
Journal of Artificial Intelligence Research
Using data and theory in multistrategy (mis) concept (ion) discovery
IJCAI'97 Proceedings of the 15th international joint conference on Artifical intelligence - Volume 1
The role of chess in artificial intelligence research
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 1
An augmented EBL and its application to the utility problem
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Concept formation over explanations and problem-solving experience
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Learning from textbook knowledge: a case study
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Changing the rules: a comprehensive approach to theory refinement
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Knowledge level and inductive uses of chunking (EBL)
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Refinement of approximate domain theories by knowledge-based neural networks
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Adaptive pattern-oriented chess
AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2
A theory of unsupervised speedup learning
AAAI'92 Proceedings of the tenth national conference on Artificial intelligence
Computing least common subsumers in description logics
AAAI'92 Proceedings of the tenth national conference on Artificial intelligence
Finding accurate frontiers: a knowledge-intensive approach to relational learning
AAAI'93 Proceedings of the eleventh national conference on Artificial intelligence
ITWP'03 Proceedings of the 2003 international conference on Intelligent Techniques for Web Personalization
Artificial Intelligence in Medicine
Hi-index | 0.00 |
This paper formalizes a new learning-from-examples problem: identifying a correct concept definition from positive examples such that the concept is some specialization of a target concept defined by a domain theory. It describes an empirical study that evaluates three methods for solving this problem: explanation-based generalization (EBG), multiple example explanation-based generalization (mEBG), and a new method, induction over explanations (IOE). The study demonstrates that the two existing methods (EBG and mEBG) exhibit two shortcomings: (a) they rarely identify the correct definition, and (b) they are brittle in that their success depends greatly on the choice of encoding of the domain theory rules. The study demonstrates that the new method, IOE, does not exhibit these shortcomings. This method applies the domain theory to construct explanations from multiple training examples as in mEBG, but forms the concept definition by employing a similarity-based generalization policy over the explanations. IOE has the advantage that an explicit domain theory can be exploited to aid the learning process, the dependence on the initial encoding of the domain theory is significantly reduced, and the correct concepts can be learned from few examples. The study evaluates the methods in the context of an implemented system, called Wyl2, which learns a variety of concepts in chess including “skewer” and “knight-fork.”