Korean AI Association

  >   학술행사   >   국내학술대회


기조 & 초청강연
Plenary Talk 1



Pradeep Ravikumar
Machine Learning Department, School of Computer Science, Carnegie Mellon University
Title : Neuro-Causal Models
Abs :
We discuss neuro-causal models, a novel neuro-symbolic model architecture that uses a synthesis of deep generative models and causal graphical models to automatically infer higher level symbolic information from lower level “raw features”, while also allowing for rich relationships among the symbolic variables. Neuro-causal models retain the flexibility of modern deep neural network architectures while simultaneously capturing statistical semantics such as identifiability and causality, which are important to discuss ideal, target representations and their tradeoffs. We provide conditions under which this entire architecture can be recovered uniquely. We also discuss efficient algorithms to learn representations using this architecture, and provide experiments illustrating the algorithms in practice.
Pradeep Ravikumar is a Professor in the Machine Learning Department, School of Computer Science at Carnegie Mellon University. He was previously an Associate Director at the Center for Big Data Analytics, at the University of Texas at Austin. His thesis has received honorable mentions in the ACM SIGKDD Dissertation award and the CMU School of Computer Science Distinguished Dissertation award. He is a Sloan Fellow, a Siebel Scholar, and a recipient of the NSF CAREER Award. He is Associate Editor-in-Chief for IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), and incoming Editor-in-Chief for the Journal of Machine Learning Research.


Plenary Talk 2


Masashi Sugiyama
RIKEN Center for Advanced Intelligence Project.

Department of Complexity Science and Engineering, Graduate School of Frontier Sciences,
The University of Tokyo.
Title : Towards Trustworthy Machine Learning
When training and deploying machine learning systems in the real world, we face various types of uncertainty.  For example, the available training data may contain insufficient information, label noise, and bias.  In this talk, I will give an overview of our research on trustworthy machine learning, including weakly supervised classification, noisy label classification, and transfer learning.
Masashi Sugiyama received his Ph.D. in Computer Science from the Tokyo Institute of Technology in 2001.  He has been a professor at the University of Tokyo since 2014, and also the director of the RIKEN Center for Advanced Intelligence Project (AIP) since 2016. He is (co-)author of Machine Learning in Non-Stationary Environments (MIT Press, 2012), Density Ratio Estimation in Machine Learning (Cambridge University Press, 2012),  and Machine Learning from Weak Supervision (MIT Press, 2022). In 2022, he received the Award for Science andTechnology from the  Japanese Minister of Education, Culture, Sports, Science and Technology. He was program co-chair of the Neural Information Processing Systems (NeurIPS) conference in 2015 and the International Conference on Artificial Intelligence and Statistics (AISTATS) in 2019.



Invited Talk 



정우용 대표이사(하이브IM)
Title : Technology meets Entertainment in HYBE.

Abs : 하이브IM에서 진행 중인 기술과 엔터테인먼트의 만남에 대해 사례 중심으로 살펴본다.
  • 2021.02~ 하이브IM 대표이사
  • 2016 넥슨코리아, 디렉터
  • 2014 버스커랩, 대표이사
  • 2012 아이나게임즈, 제작 총괄
  • 2005 네오위즈, PD
  • 2003 넥슨, 프로그래머