Research Colloquium

Speaker:

  Dr. Arthur Choi

Title:
   Using Symbolic Artificial Intelligence to Explain Statistical Machine Learning



Abstract:
     Recent and rapid advances in Artificial Intelligence (AI), particularly in the form of deep neural networks, has opened many new possibilities, but it has also brought with it many new challenges. In particular, it has become increasingly apparent that while deep neural networks are highly performant, they can also be opaque and brittle.  We do not have enough understanding of why and when they work well, and why they may fail completely when faced with new situations not seen in the training data.  In this talk, we propose a symbolic approach to explaining the behavior and verifying the properties of machine learning models, which is based on sustained advances in logical and probabilistic reasoning.  We show how our approach facilitates the analysis of a neural network, helping us to understand its behavior, and in turn, providing directions towards learning better and more robust models.



Bio:
   Arthur Choi is a research scientist in the Computer Science Department at UCLA.  He obtained his PhD from UCLA in 2010.  His research interests are in logical and probabilistic approaches to reasoning, machine learning, tractable knowledge representations, and most recently in explainable artificial intelligence (XAI).  He has led medal-winning teams in international probabilistic inference competitions.  He has served as an SPC/PC member at conferences such as IJCAI, AAAI, UAI, NeurIPS, and ICML.

 

How to participate this via Webex :

Time: 1:00 PM - 2:20 PM Thursday, Apr 30 2020 (UTC-04:00) Eastern Time (US & Canada)

Top of Form

Meeting link:

https://gsumeetings.webex.com/gsumeetings/j.php?MTID=m60185fe33ad004cada6c8fd2adff94bd

Meeting number: 474 407 402

Password: xrR87NCk5fq

More ways to join

Join by video system

Dial 474407402@gsumeetings.webex.com

You can also dial 173.243.2.68 and enter your meeting number.

Join by phone

+1-415-655-0002 US Toll

+1-415-655-0002 US Toll

Access code: 474 407 402

 

From: Xiaojun Cao <[log in to unmask]>
Sent: Wednesday, April 29, 2020 11:04 AM
To: Tammie T Dudley <[log in to unmask]>; Yingshu Li <[log in to unmask]>
Subject: RE: NextGen-AI research presentation by Dr. Arthur Choi (Apr.30, 1-2:20pm)

 

Tammie,

 

This is the job talk from another CS candidate tomorrow.

Please share it with the students.

Thanks a lot!

 

 

From: Xiaojun Cao
Sent: Monday, April 27, 2020 2:55 PM
To: Tammie T Dudley <[log in to unmask]>; Yingshu Li <[log in to unmask]>
Subject: NextGen-AI research presentation by Dr. Razvan Bunescu (April 28, 11-12:30am)

 

Tammie,

 

This is the information of tomorrow’s talk.

Please share it with the graduate students.

Thanks a lot!

 

Best,

 

--

Xiaojun (Matt)  Cao   Ph.D.

Professor

Department of Computer Science

Georgia State University

Tel: (404) 413-5732, Fax: (404) 413-5717

Web: http://www.cs.gsu.edu/cao