The max-sum classifier predicts n-tuple of labels from n-tuple of observable variables by maximizing a sum of quality functions defined over neighbouring pairs of labels and obser...
We present new results on the well-studied problem of learning DNF expressions. We prove that an algorithm due to Kushilevitz and Mansour [13] can be used to weakly learn DNF form...
Avrim Blum, Merrick L. Furst, Jeffrey C. Jackson, ...
We propose and analyze a distribution learning algorithm for variable memory length Markov processes. These processes can be described by a subclass of probabilistic nite automata...
A pattern is a string of constant and variable symbols. The language generated by a pattern is the set of all strings of constant symbols which can be obtained from by substituti...
Thomas Erlebach, Peter Rossmanith, Hans Stadtherr,...
Abstract. We extend Angluin’s algorithm for on-line learning of regular languages to the setting of timed systems. We consider systems that can be described by a class of determi...