Speaker: Shuiwang Ji, Ph.D. Associate Professor at the Department of Computer Science & Engineering at Texas A&M University.
Faculty Host: Yu Ding, TAMIDS
Abstract: Deep learning has achieved remarkable success on computer vision and natural language tasks. These successes are gradually extending to scientific fields, enabling scientists to make measurements and observations that were previously unobtainable. In this talk, the speaker will present their work on developing novel and advanced deep learning methods on images and graphs. In the image domain, the speaker will show how their methods can be used to perform augmented microscopy in which low-resolution microscopic images are transformed into high-resolution ones. In the graph domain, the speaker will demonstrate how graph neural networks can be used for molecular property prediction and drug discovery. Part of the talk is recently published in Nature Machine Intelligence.
In this talk we will discuss the foundations of a new family of machine learning methods coined as physics-informed neural networks, that aim to seamlessly bridge this gap by synthesizing incomplete physics-based models with imperfect observational data. Specifically, we will illustrate the mechanisms by which deep neural networks can be constrained to respect fundamental laws of physics, but also highlight certain pathologies and limitations that arise during this process. Strikingly, some of the latter can be addressed by exploring connections to classical methods in numerical analysis and optimization, opening the path to designing more principled algorithms and deep learning architectures that do not simply rely on guesswork. Finally, we will demonstrate the power of these methods across a range of diverse engineering applications, including problems in design optimization, heat transfer, wave propagation, cardiovascular fluid mechanics, and COVID-19 spread dynamics.
Biography: Dr. Shuiwang Ji is an Associate Professor in the Department of Computer Science & Engineering, Texas A&M University, leading the Data Integration, Visualization, and Exploration (DIVE) Laboratory. He received the Ph.D. degree in Computer Science from Arizona State University in 2010. His research interests include machine learning, deep learning, data mining, and computational biology. Dr. Ji serves as an Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), ACM Transactions on Knowledge Discovery from Data (TKDD), and ACM Computing Surveys (CSUR). He regularly serves as an Area Chair or equivalent for AAAI Conference on Artificial Intelligence (AAAI), International Conference on Learning Representations (ICLR), International Conference on Machine Learning (ICML), International Joint Conference on Artificial Intelligence (IJCAI), ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), and Annual Conference on Neural Information Processing Systems (NeurIPS). Dr. Ji is a 2014 NSF CAREER Awardee, a Distinguished Member of ACM, and a Senior Member of IEEE.
You can also click this link to join the seminar
For more information about TAMIDS seminar series, please contact Ms. Jennifer South at firstname.lastname@example.org