Particle Swarm Optimization Based Algorithm for Conditional Probability Neural Network Learning

摘要：

　　Conditional probability neural network (CPNN) has special advantage in pattern classification problems.However, how to find the optimal parameters of the CPNN to achieve better performance is an extraordinary challenge.Considering the structure feature of CPNN, we proposed a new training method based on particle swarm optimization (PSO).This method utilizes PSO to optimize the structure of CPNN and label distributions by introducing Hellinger distance between different label distributions.We applied the improved CPNN on facial age estimation.The experimental results showed that this network could increase recognition accuracy significantly.

关键词： Age Estimation Label Distribution Learning Conditional Probability Neural Network Hellinger distance Particle Swarm Optimization

作者: Junjie XU Min JIANG Qingsheng CHEN Zhongqiang HUANG Yulong DING

作者单位: Department of Cognitive Science and Fujian Provincial Key Laboratory of Brain-like Intelligent Syste School of Physics and Mechanical and Electrical Engineering.Xiamen University,P.R.China

会议类型: 国内会议

会议名称: 2015全国理论计算机科学学术年会

会议地点: 金华

会议语种:英文

页码: 1-12

在线出版日期: 2015-10-30（万方平台首次上网日期，不代表论文的发表时间）