Adaptive Training Of Feedback Neural Networks For Non-Linear Filtering

. The paper proposes a general framework which encompasses the training of neural networks and the adaptation of filters. It is shown that neural networks can be considered as general non-linear filters which can be trained adaptively, i.e. which can undergo continual training. A unified view of gradient-based training algorithms for feedback networks is proposed, which gives rise to new algorithms. The use of some of these algorithms is illustrated by examples of non-linear adaptive filtering and process identification. INTRODUCTION In recent papers [1, 2], a general framework, which encompasses algorithms used for the training of neural networks and algorithms used for the adaptation of filters, has been proposed. Specifically, it was shown that neural networks can be used adaptively, i.e. can undergo continual training with a possibly infinite number of time-ordered examples - in contradistinction to the traditional training of neural networks with a finite number of examples pres..