A GA Based Flexible ANN Architecture Design Method

摘要：

Now ANN(Artificial Neural Network) is atechnique widely used in solving AI(Artificial Intelligence) problems. In ANN design, the linking style and weights play important role, but searching a optimum network architecture and weights are still facing great challenge. GA(Genetic Algorithm) is a optimum local search criterion in searching space. In this paper, we present a new method of using GA for searching optimal ANN architecture and suitably weights.

关键词： GA ANN Architecture optimization FPGA Hardware implementation

作者: Fei Hui Chen Shi Xunying Zhang Shitan Huang

作者单位: Xi’an Institute of Microelectronics Technology, 710054, Xi’an, Shaanxi, China

会议类型: 国际会议

会议名称: The Second International Symposium on Intelligence Computation and Applications(ISICA 2007)(第二届智能计算及其应用国际会议)

会议地点: 武汉

会议语种:英文

在线出版日期: 2007-09-21（万方平台首次上网日期，不代表论文的发表时间）