ATTRIBUTED RELATIONAL GRAPH MATCHING NEURAL NETWORK AND ITS APPLICATION
C Wang · 1994
A new method of Error-calibrated and Attributed Relational Matchina NeuralNetwork (EARGMNN) has been developed in this paper. Attributed Relational Graphs (ARG), there are direction arcs and multi--arcs. So ARG is asymmetric, but theHopfield Net is symmetry. After redefining the distances of node feature and noderelational arc feature, we solved these asymmetry problem. At the same time, theidea of error-calibration has been introduced into neural network. Then the net canbe used as random semantic net matching. The analogue annealing method has beenintroduced in EARGMNN model also, the test results are quite satisfactory.