In this work we present a novel approach for learning nonhomogenous textures without facing the unlearning problem. Our learning method mimics the human behavior of selective lear...
In this paper we introduce a novel approach to manifold alignment, based on Procrustes analysis. Our approach differs from "semisupervised alignment" in that it results ...
Many of today's best classification results are obtained by combining the responses of a set of base classifiers to produce an answer for the query. This paper explores a nov...
Web2.0 has revolutionized the way we use the Web by opening the doors of collaborative learning and direct communication and making the web an open source for learning and exchangi...
We present an expressive agent design language for reinforcement learning that allows the user to constrain the policies considered by the learning process.The language includes s...