We have previously proposed a trajectory model which is based on a mixture density network (MDN) trained with target variables augmented with dynamic features together with an algo...
— By combining a low-order model of forecast errors, the extended Kalman filter, and classical continuous optimization, we develop an integrated methodology for planning mobile ...
Abstract. In recent years, there has been a great deal of work in modeling audio using non-negative matrix factorization and its probabilistic counterparts as they yield rich model...
We explore the implications of supporting bags (i.e. multisets) in a data model and associated query language, and present some formal results concerned with the algebraic propert...
This paper extends previous work on the compilation of higher-order imperative languages into digital circuits [4]. We introduce concurrency, an essential feature in the context o...