In the past decade, connectionism has proved its efficiency in the field of static pattern recognition. The next challenge is to deal with spatiotemporal problems. This article presents a new connectionist architecture, RST (réseau spatio temporel [spatio temporal network]), with such spatiotemporal capacities. It aims at taking into account at the architecture level both spatial relationships (e.g., as between neighboring pixels in an image) and temporal relationships (e.g., as between consecutive images in a video sequence). Concerning the spatial aspect, the network is embedded in actual space (two) or three-dimensional-, the metrics of which directly influence its structure through a connection distribution function. For the temporal aspect, we looked toward biology and used a leaky-integrator neuron model with a refractory period and postsynaptic potentials. The propagation of activity by spatiotemporal synchronized waves enables RST to perform motion detection and localization in sequences of video images.
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 speciM section.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.