A framework for learning constraints: Preliminary report
PRICAI '96 Selected Papers from the Workshop on Reasoning with Incomplete and Changing Information and on Inducing Complex Representations: Learning and Reasoning with Complex Representations
Constraint Processing
A constraint seeker: finding and ranking global constraints from examples
CP'11 Proceedings of the 17th international conference on Principles and practice of constraint programming
| Hi-index | 0.00 |
In this paper we view interactive constraint acquisition as the process of learning constraints from examples and focus on the roles played by both the user and the system during an interactive session. We consider our user as a teacher who provides positive examples to an automated constraint acquisition system. Each positive example represents a solution to the target constraint network we are trying to acquire. In this paper we compare a number of ways in which users can choose examples to be presented to a constraint acquisition system and identify the best strategy for the user to adopt. We recognize that not every user will naturally be able to assume the best profile and therefore present an assistant that can help a user construct good examples. We show that the assistant helps, in a significant manner, a human user trying to describe a target constraint network using a very small number of examples.