<i>A posteriori</i> error learning in nonlinear adaptive filters

作     者：Mandic, DP Chambers, JA 

作者机构：Univ London Imperial Coll Sci Technol & Med Dept Elect & Elect Engn Commun & Signal Proc Grp London England 

出 版 物：《IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING》 (IEE Proc Vision Image Signal Proc)

年 卷 期：1999年第146卷第6期

页      面：293-296页

核心收录：

主　　题：prediction theory adaptive filters gradient-based learning algorithms feedforward neural networks adaptation algorithms lower bounds gradient methods error analysis a posteriori error learning Neural nets Filtering methods in signal processing neuron Neural computing techniques upper bounds feedforward neural nets recurrent neural networks filtering theory learning (artificial intelligence) nonlinear filters recurrent neural nets nonlinear adaptive filters general nonlinear activation function Signal processing theory 

摘      要：The authors provide relationships between the a priori and a posteriori errors of adaptation algorithms for real-time output-error nonlinear adaptive filters realised as feedforward or recurrent neural networks. The analysis is undertaken for a general nonlinear activation function of a neuron, and for gradient-based learning algorithms, for both a feedforward (FF) and recurrent neural network (RNN). Moreover, the analysis considers both contractive and expansive forms of the nonlinear activation functions within the networks. The relationships so obtained provide the upper and lower error bounds for general gradient based a posteriori learning in neural networks.