Neural nets for sensor and motor trajectories

Abstract

The use of artificial neural networks for the management of sensory and motor trajectories is introduced. In the approach presented, the space-time functions representing the trajectories are separated so that the spatial parameters are stored in one neural map and the time parameters are stored in a second neural map. An approach called a neural triangular lattice is suggested for implementing the neural maps.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>