We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...
We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resul...
Michael Karlen, Jason Weston, Ayse Erkan, Ronan Co...
This paper proposes a method of crawling Web servers connected to the Internet without imposing a high processing load. We are using the crawler for a field survey of the digital ...
Katsuko T. Nakahira, Tetsuya Hoshino, Yoshiki Mika...
This dissertation research explores the invocation of emotional support from friends and family for parents who have a baby in a Neonatal Intensive Care Unit, through the use of t...
In this paper, we propose a statistical optimization framework for transmitting audio sequences over wireless links. Our proposed framework protects audio frames against both temp...