Conference ID: 935-096-67063
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.
Zuowei Shen is Tan Chin Tuan Centennial Professor at National University of Singapore, whose research speciality is on mathematical foundation of data science, especially in the areas of approximation and wavelet theory, image processing and compressed sensing, computer vision and machine learning. He was an invited speaker at the International Congress of Mathematicians (ICM) in 2010, and at the 8th International Congress on Industrial and Applied Mathematics (ICIAM) in 2015. He is a Fellow of the Singapore National Academy of Science, the World Academy of Sciences, the Society for Industrial and Applied Mathematics, the American Mathematical Society.