Sciweavers

IJCAI
1989
13 years 6 months ago
Utilization Filtering: A Method for Reducing the Inherent Harmfulness of Deductively Learned Knowledge
This paper highlights a phenomenon that causes deductively learned knowledge to be harmful when used for problem solving. The problem occurs when deductive problem solvers encount...
Shaul Markovitch, Paul D. Scott
AAAI
1990
13 years 6 months ago
Exploiting Locality in a TMS
This paper presents a new approach for exploiting Truth Maintenance Systems(TMSs) which makes them simpler to use without necessarily incurring a substantial performance penalty. ...
Johan de Kleer
AAAI
1998
13 years 6 months ago
Supermodels and Robustness
When search techniques are used to solve a practical problem, the solution produced is often brittle in the sense that small execution difficulties can have an arbitrarily large e...
Matthew L. Ginsberg, Andrew J. Parkes, Amitabha Ro...
ECAI
1994
Springer
13 years 9 months ago
Combining the Lazy Label Evaluation with Focusing Techniques in an ATMS
For large problems the ATMS often becomes the main resource consumer in any reasoning system. We propose an architecture (the 2vATMS) that combines the advantages of two techniques...
Mugur M. Tatar
ECAI
2000
Springer
13 years 9 months ago
On Efficiency of Learning: A Framework and Justification
Abstract. A conceptual framework, whose goal is the improvement of efficiency of machine learning, is presented. The framework is designed in a broader context of problem solver (P...
Jindrich Bucha
ECML
2005
Springer
13 years 10 months ago
Using Advice to Transfer Knowledge Acquired in One Reinforcement Learning Task to Another
We present a method for transferring knowledge learned in one task to a related task. Our problem solvers employ reinforcement learning to acquire a model for one task. We then tra...
Lisa Torrey, Trevor Walker, Jude W. Shavlik, Richa...