This paper presents a short overview of blended learning, showing arguments for and against these concepts. Potential blended learning scenarios are described that vary depending o...
We consider a parallel decomposition technique for solving the large quadratic programs arising in training the learning methodology Support Vector Machine. At each iteration of th...
In structured prediction problems, outputs are not confined to binary labels; they are often complex objects such as sequences, trees, or alignments. Support Vector Machine (SVM) ...
Abstract. We introduce a new class of recurrent, truly sequential SVM-like devices with internal adaptive states, trained by a novel method called EVOlution of systems with KErnel-...
This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled v...