next up previous
Next: INTRODUCTION

LEARNING TO GENERATE ARTIFICIAL FOVEA TRAJECTORIES FOR TARGET DETECTION
( International Journal of Neural Systems, 2(1 & 2):135-141, 1991. Figures here! )

JÜRGEN SCHMIDHUBER 1, TUM
RUDOLF HUBER, TUM

Abstract:

It is shown how `static' neural approaches to adaptive target detection can be replaced by a more efficient and more sequential alternative. The latter is inspired by the observation that biological systems employ sequential eye-movements for pattern recognition. A system is described which builds an adaptive model of the time-varying inputs of an artificial fovea controlled by an adaptive neural controller. The controller uses the adaptive model for learning the sequential generation of fovea trajectories causing the fovea to move to a target in a visual scene. The system also learns to track moving targets. No teacher provides the desired activations of `eye-muscles' at various times. The only goal information is the shape of the target. Since the task is a `reward-only-at-goal' task , it involves a complex temporal credit assignment problem. Some implications for adaptive attentive systems in general are discussed.




next up previous
Next: INTRODUCTION
Juergen Schmidhuber 2003-02-21

Back to Reinforcement Learning page
Back to main page on Learning attentive vision