Abstract: While neural networks have become ubiquitous and used in nearly every major area of study, the theoretical foundations of them are still shaky, with the most major theory finding on them happening in 2000. In this talk I will introduce some major theoretical findings about neural networks and discuss the open questions and hopefully convince some of the theory-focused researchers that it might be worth their while to study these questions.Join the Seminar
The CICS Theory Seminar is free and open to the public. If you are interested in giving a talk, please email Cameron Musco or Rik Sengupta. Note that in addition to being a public lecture series, this is also a one-credit graduate seminar (CompSci 891M) that can be taken repeatedly for credit.