Research of BP neural network genetic algorithm based on MapReduce in nonlinear system identification

Research of BP neural network genetic algorithm based on MapReduce in nonlinear system identification

Chen Chunping Chaya Champion Shandandan

Some complex s nonlinear systems are often encountered in engineering applications, which are complex and difficult to be modeled accurately by mathematical methods. The three-layer BP neural network can approximate continuous function with arbitrary precision. But the BP network has the disadvantage of falling into the local optimal value, and then the genetic algorithm is added. The traditional training method of the serial BP neural network There are a lot of problems when processing the massive data, for example, it takes too long, even the memory is not enough to train. In order to solve these problems, the BP neural Network training method based on MapReduce is used.

Research of BP neural network genetic algorithm based on MapReduce in nonlinear system identification