Sort by
Refine Your Search
-
project, we aim to employ privacy-enhancing techniques to design new and efficient algorithms that can provide strong protection during the entire life cycle of ML models used on the devices
-
project, we aim to employ privacy-enhancing techniques to design new and efficient algorithms that can provide strong protection during the entire life cycle of ML models used on the devices
-
Primary supervisor Mahsa Salehi Research area Temporal Analytics Lab The existing deep learning based time series classification (TSC) algorithms have some success in multivariate time series, their
-
Primary supervisor Mahsa Salehi Research area Temporal Analytics Lab The existing deep learning based time series classification (TSC) algorithms have some success in multivariate time series, their
-
at an ambitious goal - designing secure and privacy-enhancing algorithms and framework for FL and applying our designs into real-world applications. To achieve this goal, we expect to deeply and
-
study the properties of such explanations, present algorithms for automatically computing them as well as extensions to existing frameworks and evaluate their performance both empirically and through
-
study the properties of such explanations, present algorithms for automatically computing them as well as extensions to existing frameworks and evaluate their performance both empirically and through
-
detection and monitoring, invariant and distributionally robust representation learning algorithms, and deployment-time calibration with uncertainty quantification using approaches such as conformal
-
investment planning, we support clever algorithms and data crunching to make decisions automatically and to let humans make informed decisions, too. Across FIT, we have at least one dozen academics
-
technologies through theory and simulation and/or experimental design and testing; developing new image reconstruction algorithms for providing more information with less radiation; and applying our techniques