An-FPGA Based Classification System by Using a Neural Network and an Improved Particle Swarm Optimization Algorithm
Tuan Linh Dang, Yukinobu Hoshino · 2016
This paper presents a development of a soft intelligent system on chip. This system is used to solve the classification problem. In this system, a neural network is trained by the particle swarm optimization (PSO) algorithm. This algorithm is hardware implemented on a real device. An improved version of the standard PSO algorithm called the PSOseed algorithm is also introduced in this paper in order to reduce the possibility when the standard PSO gets stuck in the local minimum. The experimental results show that the neural network trained by the particle swarm optimization algorithm was successful hardware implemented. In addition, the PSOseed algorithm also obtained a better performance than the standard PSO algorithm in our experiments.