Bayesian Deep Learning for Integrated Intelligence: Bridging the Gap between Perception and Inference

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


PhD Thesis Defence


Title: "Bayesian Deep Learning for Integrated Intelligence: Bridging the Gap 
between Perception and Inference"

By

Mr. Hao WANG


Abstract

While perception tasks such as visual object recognition and text understanding 
play an important role in human intelligence, the subsequent tasks that involve 
inference, reasoning, and planning require an even higher level of 
intelligence. The past few years have seen major advances in many perception 
tasks using deep learning models. In terms of higher-level inference, however, 
probabilistic graphical models, with their ability to expressively describe 
properties of variables and various probabilistic relations among variables, 
are still more powerful and exible.

To achieve integrated intelligence that involves both perception and inference, 
we have been exploring along a research direction, which we call Bayesian deep 
learning, to tightly integrate deep learning and Bayesian models within a 
principled probabilistic framework. In this thesis, I will present this 
proposed unied framework and some of our work on Bayesian deep learning with 
various applications in recommendation, link prediction, topic models, and 
representation learning.


Date:			Thursday, 10 August 2017

Time:			10:00am - 12:00noon

Venue:			Room 2611
 			Lifts 31/32

Chairman:		Prof. Wai-Ho Mow (ECE)

Committee Members:	Prof. Dit-Yan Yeung (Supervisor)
 			Prof. Yangqiu Song
 			Prof. Raymond Wong
 			Prof. Kani Chen (MATH)
 			Prof. Irwin King (Comp. Sci. & Engg., CUHK)


**** ALL are Welcome ****