We consider a parsed text corpus as an instance of a labelled directed graph, where nodes represent words and weighted directed edges represent the syntactic relations between the...
We present a novel learning framework for pipeline models aimed at improving the communication between consecutive stages in a pipeline. Our method exploits the confidence scores ...
High dimensionality of belief space in Partially Observable Markov Decision Processes (POMDPs) is one of the major causes that severely restricts the applicability of this model. ...
Abdeslam Boularias, Masoumeh T. Izadi, Brahim Chai...
We examine whether or not it is possible to determine, recognize and/or report the emotional state of a group of people through touch and/or body motion. We present the initial des...
Omar Mubin, Abdullah Al Mahmud, Christoph Bartneck
Confidence-weighted (CW) learning [6], an online learning method for linear classifiers, maintains a Gaussian distributions over weight vectors, with a covariance matrix that repr...