Multilayer feedforward networks are universal approximators
Neural Networks
Design problem solving: a task analysis
AI Magazine
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
The essence of constraint propagation
Theoretical Computer Science
Machine Learning
CP '02 Proceedings of the 8th International Conference on Principles and Practice of Constraint Programming
Automatic Generation of Constraint Propagation Algorithms for Small Finite Domains
CP '99 Proceedings of the 5th International Conference on Principles and Practice of Constraint Programming
Automatic generation of rule-based constraint solvers over finite domains
ACM Transactions on Computational Logic (TOCL)
A CHR-based implementation of known arc-consistency
Theory and Practice of Logic Programming
The complexity of global constraints
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Finite domain constraint solver learning
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
| Hi-index | 0.00 |
In constraint-based design, components are modeled by variables describing their properties and subject to physical or mechanical constraints. However, some other constraints are difficult to represent, like comfort or user satisfaction. Partially defined constraints can be used to model the incomplete knowledge of a concept or a relation. Instead of only computing with the known part of the constraint, we propose to complete its definition by using machine-learning techniques. Because constraints are actively used during solving for pruning domains, building a classifier for instances is not enough: we need a solver able to reduce variable domains. Our technique is composed of two steps: first we learn a classifier for the constraint's projections and then we transform the classifier into a propagator. We show that our technique not only has good learning performances but also yields a very efficient solver for the learned constraint.