Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Program
-
Field
-
interdisciplinary areas. Research fields of particular interest include, but not limited to: biomedical science and engineering veterinary science computer science and data science neuroscience and neural
-
interdisciplinary areas. Research fields of particular interest include, but not limited to: biomedical science and engineering veterinary science computer science and data science neuroscience and neural
-
interdisciplinary areas. Research fields of particular interest include, but not limited to: biomedical science and engineering veterinary science computer science and data science neuroscience and neural
-
of collaborative watermarking to diffusion models and audio language models based on neural audio codecs. Studying whether watermark information can be embedded in long-term content, such as speech semantics
-
networks of nodes and parameters. This practice-based PhD investigates how AI can assist at the level of tool production by drafting procedural networks that the experienced technical artist can inspect
-
. To this end, domain decomposition techniques, uncertainty quantification, and reduced models—possibly based on neural network training—will be considered, along with the development of theoretical results
-
representations, and flow matching) for uncertainty-aware 3D reconstruction of coronary anatomy from 2D X-ray angiography; develop physics-informed neural networks and graph-based neural operators for fast
-
further appears in the approximation of various dynamical problems by tensor networks and neural networks. In all these cases, the parametrization is typically irregular, meaning that the occurring linear
-
neuroscientists pursuing advanced research and development in neuromorphic computing, artificial intelligence, and spiking neural networks across a range of applications. A strong background in theory (e.g
-
research interests. We are particularly interested in fundamental ideas that can ultimately lead to practical algorithms rather than simply applying existing neural-network architectures. Who we are looking