Synthesising timbres and changes to timbres from natural language descriptions is an interesting challenge for computer music. This paper describes the current state of an ongoing ...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Classifying the endgame positions in Chess can be challenging for humans and is known to be a difficult task in machine learning. An evolutionary algorithm would seem to be the ide...
Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels....
Background: This paper introduces the notion of optimizing different norms in the dual problem of support vector machines with multiple kernels. The selection of norms yields diff...