Sort by
Refine Your Search
-
has been a focus on individual imaging modalities (e.g., fMRI, diffusion imaging) at the exclusion of combining information across modalities. Our long-term objective is to develop a “phenotypic
-
of computing and healthcare. Methodologies of interest include: Multi-modal learning Foundation models, including large language models Agentic AI Multi-agent AI systems Transfer learning Self-supervised
-
understanding of health outcomes. This project seeks to address this critical gap in our knowledge. A key limitation of previous work has been a focus on individual imaging modalities (e.g., fMRI, diffusion
-
performance and robustness, and (ii) exemplary passion and motivation to pursue multidisciplinary research at the intersection of computing and healthcare. Methodologies of interest include: Multi-modal
-
Reality to elicit users’ preferences for innovative transport systems. Applicants with a background in behavioral analysis and mathematical modelling are encouraged to apply. Terms of employment include
-
infrastructure monitoring, as well as connected autonomous vehicles Integrating multi-modal sensor data with physics-based models Developing robust and adaptive methods for real-time parameter and state estimation
-
/functional inequalities Markov processes and stochastic analysis Theoretical analysis of neural networks and deep learning Foundations of reinforcement learning and bandit algorithms Mathematical and
-
and performance analysis, Proven track record of publications in relevant IEEE journals and conferences, Strong verbal and written skills in English, Excellent analytical and problem-solving skills and
-
tailored to dynamic, human-centered environments. They may also work with diverse signal modalities, including vision, speech, images, and physiological signals. Preferred Experience: The lab highly values
-
processes and stochastic analysis Theoretical analysis of neural networks and deep learning Foundations of reinforcement learning and bandit algorithms Mathematical and algorithmic perspectives on large