Abstract. Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of th...
Spectral voice conversion is usually performed using a single model selected in order to represent a tradeoff between goodness of fit and complexity. Recently, we proposed a new ...
A combination of several classifiers using global features for the content description of medical images is proposed. Beside well known texture histogram features, downscaled repr...
One of the challenges in delivering e-government services is to design the Web sites to make it easier for citizens to find desired information. However, little work is found to e...
Previous studies of data-driven dependency parsing have shown that the distribution of parsing errors are correlated with theoretical properties of the models used for learning an...