Labeled point pattern matching by Delaunay triangulation and maximal cliques
Pattern Recognition
Finding a maximum clique in an arbitrary graph
SIAM Journal on Computing
Stereo Correspondence Through Feature Grouping and Maximal Cliques
IEEE Transactions on Pattern Analysis and Machine Intelligence
Approximating clique is almost NP-complete (preliminary version)
SFCS '91 Proceedings of the 32nd annual symposium on Foundations of computer science
Matching Hierarchical Structures Using Association Graphs
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Comparing Structures Using a Hopfield-Style Neural Network
Applied Intelligence
Neural Networks for Combinatorial Optimization: a Review of More Than a Decade of Research
INFORMS Journal on Computing
Approximating maximum clique with a Hopfield network
IEEE Transactions on Neural Networks
Automorphism Partitioning with Neural Networks
Neural Processing Letters
Robust image based document comparison using attributed relational graphs
SPPRA '08 Proceedings of the Fifth IASTED International Conference on Signal Processing, Pattern Recognition and Applications
A competitive winner-takes-all architecture for classification and pattern recognition of structures
GbRPR'03 Proceedings of the 4th IAPR international conference on Graph based representations in pattern recognition
A novel neural network approach to solve exact and inexact graph isomorphism problems
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
| Hi-index | 0.01 |
We present an in-depth mathematical analysis of a winner-takes-all Network tailoredto the maximum clique problem, a well-known intractable combinatorial optimization problem which has practical applications in several real world domains. The analysis yields tight bounds for the parameter settings to ensure energy descent to feasible solutions. To verify the theoretical results we employ a fast annealing schedule to the WTA algorithm and show the effectiveness of the proposed approach for large scaled problems in extensive computer simulations.