Functional Link Artificial Neural Networks Filter for Gaussian Noise

摘要：

　　In this paper,FLANN(functionai link ANN) filter is presented for Gaussian noise.FLANN is a singer layer with expanded input vectors and has lower computational cost than MLP(multilayer perceptron).Three types of functional expansion are discussed.BP(back propagation algorithm) for nonlinear activation function and matrix calculation for identical activation function are exploited for training FLANN.Simulation shows that convergence is not guaranteed in BP and related to the initial weight matrix and training images,and that linear FLANN trained by matrix calculation performs better than both nonlinear FLANN trained by BP and Wiener filter in detail region in environment of Gaussian noise.

关键词： FLANN BPNN Denoising Gaussian noise

作者: Guo Yuanhua Huang Chunlun

作者单位: School of Automation University of Electronic Science and Technology of China Chengdu,Sichuan,China School of Energy Science and Engineering University of Electronic Science and Technology of China Ch

会议类型: 国际会议

会议名称: 2013 2nd International Conference on Computer Science and Electronics Engineering(ICCSEE2013)(2013年第二届计算机科学与电子工程国际会议)

会议地点: 杭州

会议语种:英文

页码: 2028-2032

在线出版日期: 2013-03-22（万方平台首次上网日期，不代表论文的发表时间）