Abstract—Learning dynamical systems is one of the important problems in many fields. In this paper, we present an algorithm for learning non-linear dynamical systems which works...
Multi-label learning is useful in visual object recognition when several objects are present in an image. Conventional approaches implement multi-label learning as a set of binary...
In many multi agent learning problems, it is difficult to determine, a priori, the agent reward structure that will lead to good performance. This problem is particularly pronoun...
We develop a semi-supervised learning method that constrains the posterior distribution of latent variables under a generative model to satisfy a rich set of feature expectation c...
The paper aims at illustrating the original technical solution provided within an academic institute in order to manage teaching activities, encompassing the coordination of projec...