DLS - Masashi Sugiyama, "Towards Reliable Machine Learning from Imperfect Training Data"

Abstract:
Recent advances in machine learning (ML) have revolutionized various fields by enabling systems to learn complex patterns, make intelligent decisions, and generate creative outputs. The selection of ML-related research for the 2024 Nobel Prizes in Physics and Chemistry marks a historic milestone. However, as the capabilities of ML continue to expand, concerns regarding its safety have become increasingly prominent in society. To ensure the responsible advancement of information technology, it is crucial to elucidate the inference mechanisms of ML systems mathematically. In this lecture, I will discuss the reliable deployment of ML systems to maintain consistent performance when training data is weak, noisy, or biased. Specifically, I will provide an overview of our recent research in weakly supervised learning, noisy-label learning, and transfer learning. Finally, I will explore how ML research should be further developed in the era of large foundation models. 

Bio: 
Masashi Sugiyama received his Ph.D. in Computer Science from Tokyo Institute of Technology, Japan, in 2001. After serving as an assistant and associate professor at the same institute, he became a professor at the University of Tokyo in 2014. Since 2016, he has also served as the director of the RIKEN Center for Advanced Intelligence Project. His research interests include theories and algorithms of machine learning. He was awarded the Japan Academy Medal in 2017 and the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology of Japan in 2022.