Dr. Trilce Estrada (https://www.cs.unm.edu/~estrada/index.php) is visiting us via Zoom from U. New Mexico.

Title: Challenges and Opportunities of AI-driven Computational

Science: Reproducibility, Scalability, and Trust

Abstract: As intelligent systems become pervasive and data production grows at a rate never seen before, a whole generation of scientific and medical applications is becoming increasingly reliant on Artificial Intelligence. While the ability to automatically learn from data is driving advances in science, medicine, and engineering, especially for scenarios that are computationally expensive and hard to model, it is important to understand the pitfalls and limitations of modern machine learning methodologies and steer away from black-box type of solutions. In this talk we present three case studies, where AI and computational science coexist, and highlight one or more pitfalls in the pursuit of reproducibility, scalability, and trust.

Dr. Estrada is available for individual or group meetings on Zoom after the talk until 14:45. Contact mkoeppe@math.ucdavis.edu for scheduling if you are interested in meeting, and for the seminar Zoom link if you are interested in attending this seminar.