LEARNING TO GENERATE ARTIFICIAL FOVEA TRAJECTORIES FOR TARGET DETECTION
International Journal of Neural Systems, 2(1 & 2):135-141, 1991.
JÜRGEN SCHMIDHUBER 1, TUM
RUDOLF HUBER, TUM
It is shown how
`static' neural approaches to adaptive target detection
can be replaced by a more efficient and more
The latter is inspired by the
observation that biological systems employ sequential eye-movements for
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
generation of fovea trajectories causing
the fovea to move to a target in a visual scene.
The system also learns to track moving targets.
provides the desired activations of `eye-muscles'
at various times. The only goal information is the shape of the target.
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.
Back to Reinforcement Learning page
Back to main page on Learning attentive vision