Perception and prediction — A connectionist model

Abstract

Generating appropriate responses to incoming stimuli is a fundamental task of an organism. However, in order to generate intelligent responses, it is important to have a deeper understanding of the environment, and make predictions based on this knowledge. Although the ability to make predictions is intrinsic in humans and many animals, it is still a difficult task for a machine with no in built knowledge about the situation. In this paper we present a biologically inspired neural network model that predicts the future trajectory of a moving object after observing its current trajectory.