We present a general PAC-Bayes theorem from which all known PAC-Bayes risk bounds are obtained as particular cases. We also propose different learning algorithms for finding linea...
Predictive State Representations (PSRs) have shown a great deal of promise as an alternative to Markov models. However, learning a PSR from a single stream of data generated from ...
Higman showed that if A is any language then SUBSEQ(A) is regular, where SUBSEQ(A) is the language of all subsequences of strings in A. We consider the following inductive inferenc...
Recognizing geographical concepts such as ridges, valleys, and contour lines is an important issue in geography learning. We provide a system for automatic recognition of such con...
This paper briefly describes how ontologies can be used to model, validate and execute IMS Learning Design. The main contribution relies on incorporate the implicit knowledge foun...