Title :
Neural network approach for solving the maximal common subgraph problem
Author :
Shoukry, Amin ; Aboutabl, Mohamed
Author_Institution :
Dept. of Comput. Sci., Alexandria Univ., Egypt
fDate :
10/1/1996 12:00:00 AM
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 :
Hopfield neural nets; computer vision; information retrieval; pattern recognition; search problems; classical sequential-search-based solutions; maximal common subgraph problem; neural network approach; two-stage Hopfield neural network; Annealing; Hopfield neural networks; Information processing; Intelligent structures; Magnetic materials; Neural networks; Neurons; Pattern matching; Pattern recognition; Temperature;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/3477.537320
