Parallel Evolutionary Asymmetric Subsethood Product Fuzzy-Neural Inference System with Applications

This paper introduces PEASuPFuNIS, a parallel evolutionary asymmetric subsethood product fuzzy neural network as an extension of ASuPFuNIS, which is implemented using a high performance LAM/MPI cluster. EASuPFuNlS employs differential evolution learning which is parallelized using a master-slave model, and the implementation is facilitated through the use of derived data-types. Parallelization of EASuPFuNIS using DE learning leads to super-linear speedups concomitant with high performance as is shown through instrumentation using two problems: the Hang function approximation problem, and the Mackey-Glass time series prediction problem. Parallelization and ran-time speedup of the EASuPFuNIS model opens up the possibility of applying this class of models to real world problem domains which was hitherto not possible with the serial version due to the requirement of large computation time.