Neural network approach for solving the maximal common subgraph problem
- 1 October 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Vol. 26 (5) , 785-790
- https://doi.org/10.1109/3477.537320
Abstract
A new formulation of the maximal common subgraph problem (MCSP), that is implemented using a two-stage Hopfield neural network, is given. Relative merits of this proposed formulation, with respect to current neural network-based solutions as well as classical sequential-search-based solutions, are discussed.Keywords
This publication has 13 references indexed in Scilit:
- Object recognition by a Hopfield neural networkIEEE Transactions on Systems, Man, and Cybernetics, 1991
- A theoretical investigation into the performance of the Hopfield modelIEEE Transactions on Neural Networks, 1990
- Graph partitioning using annealed neural networksIEEE Transactions on Neural Networks, 1990
- Algebraic transformations of objective functionsNeural Networks, 1990
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Optimization by Simulated AnnealingScience, 1983
- A faster algorithm computing string edit distancesJournal of Computer and System Sciences, 1980
- An Algorithm for Subgraph IsomorphismJournal of the ACM, 1976
- Approximation des equations d'evolution du premier ordre ent par des schemas a un degre de liberteCalcolo, 1972