Proposal of a New Conception of an Elastic Neural Network and Its Application to the Solution of a Two-Dimensional Travelling Salesman Problem
In this publication, a new conception of a neural network proposed by the author was described. It belongs to the class of self-organizing networks. The theory, structure and learning principles of the network proposed were all described. Further chapters include the application of a system of two proposed neural networks for the solution of a two-dimensional Euclides’ travelling salesman problem. The feature of the neural network system proposed is an ability to avoid unfavourable local minima. The article presents graphical results of the evaluation of the neural network system from the initialization point to the determination of the selected TSP instance.
Unable to display preview. Download preview PDF.
- 1.Kohonen, T.: Selforganization and associative memory, 2nd edn. Springer Series in Information Science. Springer, Heidelberg (1988)Google Scholar
- 2.Kohonen, T.: The Self-Organizing Map. Proceedings of the IEEE (special issue on Neural Networks) 78 (1990)Google Scholar
- 3.Fritzke, B., Wilke, P.: FLEXMAP - neural network with linear time and space complexity for the travelling salesman problem. In: Proc. Int. Joint Conference of Neural Networks, Singapore, pp. 929–934 (1991)Google Scholar
- 4.Kacalak, W., Wawryn, K.: Some aspects of the modified competitive self learning neural network algorithm. In: Int. Conf. Artificial Intelligence Networks in Engineering ANNIE’94, St. Louis, USA, ASME Press, New York (1994)Google Scholar
- 5.Szatkiewicz, T., Kacalak, W.: New algorithms for trajectory optimisation of tools and objects in production systems. In: II Int. Conf. CANT, Wrocław (2003)Google Scholar
- 7.Szatkiewicz, T.: Adaptation of two-dimensional elastic neural net for travelling salesman problem. Polioptimalization and CAD, Mielno (2004)Google Scholar
- 8.Szatkiewicz, T.: Hybrid, self-adaptive optimisation system of movement of tools and objects in production systems. PhD Thesis, Technical University Of Koszalin Faculty of Mechanics, Koszalin (2005)Google Scholar