A piecewise linear dynamical functional artificial neural network (PWL-DFANN) for nonlinear adaptive time series prediction

Jose L. Figueroa,Juan E. Cousseau,R. J. P. De Figueiredo

Circuits and Systems, 2002. ISCAS 2002. IEEE International Symposium （2002）

引用 5|浏览7

暂无评分

摘要

A nonlinear adaptive time series predictor has been developed using a PWL-DFANN network (piecewise linear dynamical functional artificial neural network) for its underlying model structure. This network is so called because it is a D-FANN the activation functions of which are piecewise linear. The network has been successfully used to model and predict an important class of highly dynamic and nonstationary signals, namely speech signals.

查看译文

关键词

adaptive signal processing,neural nets,piecewise linear techniques,speech processing,time series,PWL-DFANN,activation functions,model structure,nonlinear adaptive time series prediction,nonstationary signals,piecewise linear dynamical functional artificial neural network,speech signals

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要