News and Events
Back to News Index



An Introduction to Deep Learning


In this sequence of lectures, I will give an elementary introduction to deep learning, including deep neural network models, training algorithms and applications.  I will first briefly discuss the concept of (multi-class) linearly separable sets and main ideas in two classic linear models: support vector machine and logistic regression.  I will then introduce a general function class of deep neural networks and discuss their mathematical properties such as linear independence, approximation properties and their relationship with the classic finite element methods.  As a special deep neural network, I will discuss the convolutional neural network (CNN) and its application to image classification.  In particular, I will present a new class of CNN framework, known as MgNet, which is motivated and derived from the classic multigrid methods used for solving discretized partial differential equations.  If time allows, I will discuss and analyze the commonly used training algorithm, stochastic gradient decent method (SGD), and introduce some alternative new training algorithms, known as extended regularized dual averaging (XRDA) method, that can be effectively used for training sparse deep neural networks.

Part I: 14 June 2019 (Friday) from 9:30am to 12:00pm at Room G04, Liang Y C Hall, The Chinese University of Hong Kong.

Part II: 14 June 2019 (Friday) from 2:30pm - 17:00pm at Room G04, Liang Y C Hall, The Chinese University of Hong Kong.


Back to News Index