Events Mini Calendar

Go to previous month Go to next month
  S M T W R F S
W53 27 28 29 30 31 1 2
W54 3 4 5 6 7 8 9
W2 10 11 12 13 14 15 16
W3 17 18 19 20 21 22 23
W4 24 25 26 27 28 29 30
W5 31 1 2 3 4 5 6

Today is:
Thu, May 6, 2021

MSU Events Calendar

 Choose Calendar view:   Day   Week   Month     Search   Filter

Math Seminar Series  (Conferences / Seminars / Lectures)

Zuowei Shen, National University of Singapore, will be speaking.

The seminar title is "Deep Approximation via Deep Learning."

Contact Olga Turanova ( for more information.

The primary task of many applications is approximating/estimating a function through samples drawn from a probability distribution on the input space. The deep approximation is to approximate a function by compositions of many layers of simple functions, that can be viewed as a series of nested feature extractors. The key idea of deep learning network is to convert layers of compositions to layers of tuneable parameters that can be adjusted through a learning process, so that it achieves a good approximation with respect to the input data. In this talk, we shall discuss mathematical theory behind this new approach and approximation rate of deep network; how this new approach differs from the classic approximation theory, and how this new theory can be used to understand and design deep learning network.

more information...

Location: Online via Zoom [map]
Price: free
Sponsor: Department of Mathematics
Contact: Department of Mathematics
phone pic (517) 353-0844