Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more ...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
In this paper we show that many kernel methods can be adapted to deal with indefinite kernels, that is, kernels which are not positive semidefinite. They do not satisfy Mercer...
This paper presents a novel discriminative learning technique for label sequences based on a combination of the two most successful learning algorithms, Support Vector Machines an...
Yasemin Altun, Ioannis Tsochantaridis, Thomas Hofm...
Two notions of optimality have been explored in previous work on hierarchical reinforcement learning (HRL): hierarchical optimality, or the optimal policy in the space defined by ...