Machine learning often relies on costly labeled data, and this impedes its application to new classification and information extraction problems. This has motivated the developme...
The appearance of dynamic scenes is often largely governed by a latent low-dimensional dynamic process. We show how to learn a mapping from video frames to this lowdimensional rep...
Prediction is an important task in robot motor control where it is used to gain feedback for a controller. With such a self-generated feedback, which is available before sensor rea...
The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...