Title: Deep Approximation via Deep Learing
Time：     15:00-16:00, July6 Saturday,2019
Location:   Room 1002, Science Building B
Lecturer：Prof. Shen Zuowei   

Abstract:
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 tunable 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 foundation behind this new approach of approximation; how it differs from the classic approximation theory, and how this new theory can be applied to understand and design deep learning network.

Introduction of Lectuer:
Professor Shen Zuowei, Dean of the Faculty of science, National University of Singapore, Professor Chen Zhenchuan, Centennial Memorial, academician of the National Academy of Sciences, Singapore, AMS fellow, Siam fellow. The main research fields are approximation and wavelet theory, time-frequency analysis, image science, learning theory, etc. As an internationally renowned mathematician, Professor Shen Zuowei has won the wavelet Pioneer Award, the National University of Singapore Award for outstanding scientific research and the Singapore Science Achievement Award. He was invited to give a speech at the 2010 International Congress of mathematicians and the 2015 International Congress of industrial and applied mathematics.