Parallel computer system resource planning for synthesis of neuro-fuzzy networks

Abstract

The problem of parallel computer systems resource planning in the synthesis of neuro-fuzzy networks (NFN) is considered. The model of parallel computer system resource planning for the synthesis of the NFN is developed. The developed model takes into account the following parameters: type of computer system, the number of processes that are running problem, the bandwidth of data network, the number of possible solutions to be processed in the method, the parameters of solved applied problem (the number of instances and the number of features in a given training sample). The synthesized model enables to estimate the time required parallel system to perform the method of synthesis of neuro-fuzzy networks.