***Abstract:*** This study introduces a decision-epoch-based dynamic electric autonomous dial-a-ride problem (Dyn-EADARP), in which incoming requests are collected and processed at periodic decision epochs. A key decision is not only how to serve requests, but also when to dispatch them. At each …
READ MORE***Abstract:*** With AI becoming increasingly capable, the bottleneck isn't necessarily intelligence, it's in how precisely users can communicate and direct the system. How can intelligent systems reduce the effort of expressing intent while preserving users' ability to shape the outcome? In this …
READ MORE***Abstract:*** This talk is motivated by the parameter estimation problem in control theory. The so-called input-output (I/O) differential equations are a classical tool for estimating the parameters of a parametric differential systems, assuming some experimental data are available. We present a …
READ MOREHumans can acquire abstract, reusable concepts from limited experience and extend them to unfamiliar cases. Modern deep learning systems, by contrast, often learn comparable abstractions from large labeled datasets or text corpora, in which the relevant concepts have already been named and curated …
READ MORE
français
English