Stochastic optimization algorithm with probability vector in mathematical function minimization and travelling salesman problem
Jan Pohl, Václav Jirsík, Petr Honzík · WSEAS Transactions on Information Science and Applications archive · 2010
In the paper there is introduced the newly developed optimization method the Stochastic Optimization Algorithm with Probability Vector (PSV). It is related to Stochastic Learning Algorithm with Probability Vector for artificial neural networks. Both algorithms are inspired by stochastic iterated function system SIFS for generating the statistically self similar fractals. The PSV is gradient method where the direction of individual future movement from the population is based stochastically. PSV was tested on mathematical function minimization and on the travelling sales man problem. The influence of the quantity of individuals upon the best achieved fitness function was also tested on the mathematical functions minimization.