Digital neuroimplementations of visual motion-tracking systems

Abstract

The paper describes the implementation of neural systems for visual motion tracking on a digital neurocomputing platform, i.e., the NLX420 Neural Processing Slice. The chip architecture and the problem model considered greatly facilitate the implementation task, which involves the fulfilment of critical real-time constraints. Experimental results confirm the approach validity in terms of both speed and prediction accuracy; training adjustment techniques are also examined.