Sugiyama-Yokoya-Ishida Lab at the University of Tokyo
Machine Learning and Statistical Data Analysis

How Intelligent Can Computers Become?
Theory, Algorithm, and Application of Machine Learning

With the rapid advancement of information and communication technology, intellectual activities such as reasoning and creativity, once thought to be exclusive to humans, are now being realized by computers. At the Sugiyama Laboratory, we conduct research on intelligent information processing technologies in the field of artificial intelligence, specifically known as machine learning, under the theme of "How intelligent can computers become?"

• Development of Learning Theories
  Generalization refers to the ability to handle unknown situations that have not been encountered during learning, which is essential for computers to behave intelligently. In our laboratory, we mathematically explore the mechanisms by which computers can acquire generalization abilities, based on probability theory and statistics.
  
  
• Development of Learning Algorithms
  Machine learning encompasses various challenges, including supervised learning, where computers infer from data paired with inputs and outputs; unsupervised learning, which involves learning from input-only data; and reinforcement learning, which optimizes long-term decision-making through interaction with the environment. Our laboratory develops highly practical machine learning algorithms with a solid theoretical foundation.
  
  
• Real-World Applications of Machine Learning Technology
  With the development and widespread adoption of artificial intelligence technologies, massive amounts of real-world data--—such as text, speech, images, videos, behavior, and economic data—--as well as experimental observation data in fields such as physics, chemistry, biology, medicine, astronomy, and robotics, are being collected. Our laboratory collaborates with domestic and international companies and research institutes to tackle real-world problems using cutting-edge machine learning algorithms.

Computational Imaging and Vision from Space

Yokoya Laboratory is working on image processing for computational imaging and image analysis based on computer vision and machine learning. In particular, we work on intelligent information processing to automatically extract map information, such as land cover labels and elevation models, from remote sensing images acquired by spaceborne and airborne sensors.

• Computational Imaging
  Computational imaging, which integrates sensing and computation, allows us to acquire information that cannot be obtained by hardware alone and to overcome hardware limitations, such as resolution and noise. Based on machine learning, optimization, and signal processing, we build mathematical models and develop algorithms to recover unknown original signals from incomplete observation data.
  
  
• Remote Sensing Image Analysis
  Remote sensing enables us to observe places that are inaccessible to humans; however, it is difficult to collect enough training data due to the limitations of field surveys and visual interpretation. We work on mapping and 3D reconstruction by using synthetic data from simulations and inaccurate labels with low collection costs as training data. We also work on data fusion based on deep learning to handle multimodal data obtained from different spaceborne sensors in an integrated manner.
  
  
• Towards a Sustainable Future
  We promote projects to solve global issues, including environmental problems, climate change, large-scale natural disasters, and food problems. Our goal is to contribute globally to the realization of the SDGs by solving real-world problems, such as assessing building damage during disasters, estimating biomass and carbon stocks in forests, and mapping crop types, in collaboration with related institutions and researchers in Japan and overseas.

Towards Practical and Reliable Machine Learning

Ishida Laboratory started in 2021 and is currently conducting fundamental research to develop machine learning algorithms. For example, we are building algorithms to learn from weak supervision and regularizers that can alleviate overfitting. We aim to make machine learning more practical and reliable through our research.

• Weakly Supervised Learning
  To perform ordinary supervised learning successfully, we need a large amount of labeled data. However, it is often costly to collect appropriate supervision or difficult to collect due to business constraints. To utilize an alternative source of inexpensive supervision, we are working on weakly supervised learning such as complementary-label learning and positive-confidence learning.
  
  
• Overfitting and Regularization
  In real-world applications, we often encounter many challenges that hinder us from achieving high prediction performance, such as learning from a small amount of data or learning with label noise. To cope with these situations, we are working on making machine learning more robust and proposing regularization methods to alleviate overfitting.
  
  
• Evaluation of Machine Learning Models and Data
  Given a trained machine learning model, how will we know if there is any room left for improvement? If the model has reached the best achievable error, it is meaningless to continue aiming for error improvement. Hence, knowing the best achievable error is helpful since it enables us to compare it with the trained model’s error. This can also be used as a criterion of the dataset difficulty. We are developing methods that can be used to evaluate models and datasets, such as directly estimating the best achievable error.