Time in neural networks

Abstract

After the revival of interest in connectionism in the eighties and its successful application to pattern recognition problems, the time has come to consider its role in the field of temporal processing. We present here a general overview of the field of temporal neural networks. In order to give a broad framework to this presentation, we first present general properties of time that are used by AI models. This sets out the properties of time: - on its own, - with respect to a problem, - with respect to a model. We then present a short summary of time processing in symbolic AI. The main part of this article, a classification of temporal neural models, is introduced by a short presentation of basic connectionist models. This classification is then made and several relevant examples are presented. We conclude the article with underlining the difference between temporal reasoning and neural temporal processing, and give an introduction to the following papers of this Sigart special section.