Persistent and Future Themes of Deep Learning

Abstract:  This talk will discuss a variety of recent papers, mostly from 2019.  The talk will be organized around four “themes” of deep learning:
  • Domain Independence
  • Information theory
  • Moore’s Law of AI
  • Self-Supervised Pretraining
  • Vector Quantization
  • Mutual Information Objectives
February 5 @ 12:30
12:30 pm (1h)

Discovery Building, Orchard View Room

David McAllester