We present an improved bound on the difference between training and test errors for voting classifiers. This improved averaging bound provides a theoretical justification for popu...
We present a learning algorithm for nominal data. It builds a classifier by adding iteratively a simple patch function that modifies the current classifier. Its main advantage lies...
Deictic representation is a representational paradigm, based on selective attention and pointers, that allows an agent to learn and reason about rich complex environments. In this...
Balaraman Ravindran, Andrew G. Barto, Vimal Mathew
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
In this paper we propose novel algorithms for image restoration and parameter estimation with a Generalized Gaussian Markov Random Field prior utilizing variational distribution a...
S. Derin Babacan, Rafael Molina, Aggelos K. Katsag...