Current project:
Mathematical Foundations for RISE of AI
The project is jointly funded by Halslerstiftung and ARO
While machine learning (ML) is making extraordinary demonstrations in many scientific and engineering domains with neural networks (NN), ML researchers have no delusions about the emerging weaknesses of the NN paradigm, such as robustness, interpretability, bias, and reproducibility (RISE). To this end, there is growing interest in finding robust and fair training models, where rigorous certificates of correctness can be obtained, reducing (inductive) biases and improving interpretability of the ML models, and understanding as well as overcoming the new-found difficulties in optimizing such models.
Past project:
Learning-based dimensionality reduction
The project is jointly funded by Halslerstiftung and ONRG
It seeks to enhance the applicability of adaptive sampling, overcoming the limitations of conventional techniques and simplistic models by developing techniques that learn the required information directly from data.
Aside from the broader impact in settings where data compression is relevant, we pursue a number of particularly important specific applications, including medical imaging and array signal processing, which relate to the core of cyber-human systems. This project is highly-interdisciplinary, and aims to strengthen connections between the areas of machine learning, signal processing, and optimization, and will result in new sampling theory and methods.