Optimization by extended LVQ

The authors introduce a self-generating neural network model based on Kohonen self-organizing feature maps for solving combinatorial optimization problems better than other neural network models. The model is called learning vector quantization (LVQ). In this model, the best matching neuron of the self-organizing feature maps is calculated with an energy function. The performance of this model was examined through two problems, the traveling salesman´s problem and the n-queen problem. Simulations of the traveling salesman problem have been carried out for 10 and 30 cities. The optimum solutions for the 10 and 30 cities were obtained with a probability of 100% and 52% respectively. Simulations of the n-queen problem have been obtained within 90 steps of the self-organizing cycle. The 1000-queen problem has been solved within an average of 14 minutes on a SPARCstation1