Electrical and Computer Engineering
University of Texas at Austin
2501 Speedway, EER Building, Room 6.870
Austin, Texas 78712
Hyeji Kim is an assistant professor in the department of Electrical and Computer Engineering at the University of Texas at Austin.
Prior to joining UT Austin in 2020, she spent two years at the Samsung AI Research Cambridge UK as a machine learning researcher. She received her PhD from the department of Electrical Engineering at Stanford University in 2016, under the supervision of Abbas El Gamal. Following her PhD, she worked as a postdoctoral researcher at the University of Illinois at Urbana-Champaign, hosted by Pramod Viswanath and Sewoong Oh.
Hyeji’s research interests are in information theory, machine learning, deep learning, and wireless communications, including inventing communication algorithms via deep learning, understanding the behavior of deep learning via information theory, and developing methodologies for designing lightweight high-accuracy neural network models.
- 06/2020. I had a pleasure of participating in the live panel session on Machine-learning based approaches to coding at the International Symposium on Information Theory (ISIT)
- 02/2020. I am thrilled to announce our blog [deepcomm.github.io] where we will upload tutorial-type posts on recent advances on inventing codes via deep learning
- 09/2019. Together with Stephan Ten Brink and Pramod Viswanath, I have organized Deep Learning for Communications I session at the Allerton conference
- 07/2019. I gave an invited talk “Deepcode: Feedback Codes via Deep Learning” at a special session in the International Symposium on Information Theory (ISIT)
- 02/2019. I gave an invited talk “Communication Algorithms via Deep Learning” at the Information Systems Laboratory, Stanford University
- 06/2018. Together with Sewoong Oh and Sreeram Kannan, I had a great pleasure of giving a tutorial “Information Theory and Deep Learning: an Emerging Interface” (Slides, Video recording) at the International Symposium on Information Theory (ISIT)