ARCS Forward - Machine Learning and Algorithms
Tuesday, February 15, 2022, at 12:00 PM ET/11:00 AM CT/10:00 AM MT/9:00 AM PT/7:00 AM HT
ARCS Forward events are personal and intimate conversations between members, current scholars, and other outstanding scientists in all STEM fields. These events are held virtually over Zoom. This month's speakers are ARCS Scholars Jadie Adams, Nicholas "Nick" Heller, and Biraj Pandey. This event will be moderated by Rebecca McNeilly.
Jadie Adams is a third-year PhD student in the Scientific Computing and Imaging Institute at the University of Utah. Her research combines machine learning theory and image processing techniques for biomedical data analysis. Specifically, she is working on creating statistical shape models from 3D anatomy scans (such as CT or MRI) to aid in pathology detection and diagnosis. In her recent work, she has adapted Bayesian techniques for uncertainty quantification to estimate model confidence, making predictions more usable and interpretable. She believes in the potential for computer vision and probabilistic modeling to make medical diagnosis and analysis more accurate and accessible.
Nicholas "Nick" Heller is a PhD Candidate in Computer Science at the University of Minnesota. His research focuses on the development and validation of clinical prediction models for risk stratification and treatment planning in genitourinary cancer, especially renal cell carcinoma. In particular, he is interested in the use of deep learning to incorporate tumor appearance into prediction models in more expressive and objective ways while maintaining transparency and biological plausibility. Nicholas served as the lead organizer for the MICCAI Kidney Tumor Segmentation Challenge (KiTS) in 2019 and 2021.
Biraj Pandey is a PhD Candidate in Applied Mathematics at the University of Washington. He works at the intersection of neuroscience, machine learning, and applied mathematics. He builds theories of learning in sensory areas of the brain using techniques from artificial intelligence (AI) and uses those theories in turn to build more efficient AI models. Another direction of his research is to rigorously understand why current AI models are effective using techniques from approximation theory, dynamical systems theory, and mathematical statistics. Outside research, he serves as the lead co-ordinator of his department's Diversity, Equity, and Inclusion (DEI) committee.