Robotic controllers take advantage from neural network learning capabilities as long as the dimensionality of the problem is kept moderate. This paper explores the possibilities of...
In this study we deal with the mixing problem, which concerns combining the prediction of independently trained local models to form a global prediction. We deal with it from the ...
Genetic Programming offers freedom in the definition of the cost function that is unparalleled among supervised learning algorithms. However, this freedom goes largely unexploited...
To meet the needs for large-scale, high-quality learning contents, needless to say, we have to sharpen authoring tools. Authoring process can be roughly divided into two phases, a ...
We design and analyze interacting online algorithms for multitask classification that perform better than independent learners whenever the tasks are related in a certain sense. W...