A Survey on Neural Architecture Search

PhD Qualifying Examination


Title: "A Survey on Neural Architecture Search"

by

Mr. Han SHI


Abstract:

Deep Learning has emerged as a milestone in machine learning community due 
to its remarkable ability in a variety of tasks, such as computer vision 
and neural language process. It has been demonstrated that the 
architecture of neural network influences the performance significantly 
and thus it's important to determine the architecture structure. At the 
beginning, most practical architectures are designed manually, which is
  heavily time-consuming and resource-intensive. To alleviate the issue, 
neural architecture search (NAS) has aroused significant interest 
recently, which aims to achieve potential neural architectures 
automatically. In this survey, we provide an overview of existing works 
related with neural architecture search and introduce its three main 
components: search space, search strategy and performance measure. As for 
each component, we classify and list the difference of each work and 
present a comprehensive discussion.


Date:			Friday, 31 July 2020

Time:                  	3:00pm - 5:00pm

Zoom Meeting:		https://hkust.zoom.us/j/5599077828

Committee Members:	Prof. James Kwok (Supervisor)
  			Prof. Nevin Zhang (Chairperson)
  			Dr. Qifeng Chen
 			Prof. Tong Zhang


**** ALL are Welcome ****