Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
We present a novel framework for recognizing repetitive
sequential events performed by human actors with strong
temporal dependencies and potential parallel overlap. Our
solutio...
We present a component-based description language for heterogeneous systems composed of several data flow processing components and a unique eventbased controller. Descriptions a...
We define a general notion of a fragment within higher order type theory; a procedure for constraint satisfiability in combined fragments is outlined, following Nelson-Oppen sche...
We extend the alternating-time temporal logics ATL and ATL with strategy contexts and memory constraints: the first extension makes strategy quantifiers to not “forget” the s...
Thomas Brihaye, Arnaud Da Costa Lopes, Franç...