The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
The problem of learning with positive and unlabeled examples arises frequently in retrieval applications. We transform the problem into a problem of learning with noise by labelin...
We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that impl...
The representation used by a learning algorithm introduces a bias which is more or less well-suited to any given learning problem. It is well known that, across all possible probl...