Alternative Analysis Networking: A Multicharacterization Algorithm

A neural network technique known as Kohonen unsupervised training is coupled with a modified version of the particle swarm optimization technique in an effort to develop an algorithm capable of finding multiple optimal solutions for a given problem. The ability to find multiple optimal solutions is of interest in many different applications, such as complex engineering design problems, where it´s beneficial to analyze more than one potential design or solution. The results of five example problems of increasing difficulty validate the Alternative Analysis Networking algorithm´s functionality. This algorithm is an efficient and robust technique, and appears to be the first capable of performing the task of finding multiple optimal solutions as efficiently as typical stochastic-based optimizers.