A SURVEY ON VISUALIZATION FOR EXPLAINABLE CLASSIFIERS

PhD Qualifying Examination


Title: "A SURVEY ON VISUALIZATION FOR EXPLAINABLE CLASSIFIERS"

by

Mr. Yao MING


Abstract:

Classification is a fundamental problem in machine learning, data mining 
and computer vision. In practice, interpretability is a desirable property 
of classification models (classifiers) in critical areas, such as 
security, medicine and finance. For instance, a quantitative trader may 
prefer a more interpretable model with less expected return due to its 
predictability and low risk. Unfortunately, the best-performing 
classifiers in many applications (e.g., deep neural networks) are complex 
machines whose predictions are difficult to explain. Thus, there is a 
growing interest in using visualization to understand, diagnose and 
explain intelligent systems in both academia and in industry. Many 
challenges need to be addressed in the formalization of explainability, 
and the design principles and evaluation of explainable intelligent 
systems.

The survey starts with an introduction to the concept and background of 
explainable classifiers. Efforts towards more explainable classifiers are 
categorized into two: designing classifiers with simpler structures that 
can be easily understood; developing methods that generate explanations 
for already complicated classifiers. Based on the life circle of a 
classifier, we discuss the pioneering work of using visualization to 
improve its explainability at different stages in the life circle. The 
survey ends with a discussion about the challenges and future research 
opportunities of explainable classifiers.


Date:			Monday, 30 October 2017

Time:                  	10:00am - 12:00noon

Venue:                  Room 4472
                         Lifts 25/26

Committee Members:	Prof. Huamin Qu (Supervisor)
 			Prof. James Kwok (Chairperson)
 			Dr. Yangqiu Song
 			Prof. Nevin Zhang


**** ALL are Welcome ****