NCSA staff who would like to submit an item for the calendar can email newsdesk@ncsa.illinois.edu.
Recent advances combining simulation, optimization, and artificial intelligence have enabled the treatment of engineering design as a generative learning problem. This seminar will discuss and demonstrate techniques including conditional variable autoencoders, transformer surrogates, and reinforcement learning as meta-optimization.
About the speaker: Jordan Smart is an Assistant Professor in the Department of Aerospace Engineering at the University of Illinois Urbana-Champaign. He is the Principal Investigator of the Experimental Design Engineering (EDEn) Lab. He obtained his Ph.D. in Aeronautics and Astronautics from Stanford University, and is the co-founder of both Stargazer Design Technologies, Inc. and Aerospace Research Community, LLC.