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

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

With the dramatic performance improvement of information and communication technology, intelligent information processing that can be done only by humans is becoming possible also by computers. Under the theme of "how intelligent can computers be?", Sugiyama Laboratory is working on various research topics related to intelligent data analysis, called machine learning, in the field of artificial intelligence.

• Construction of Learning Theory
  Generalization is the ability to be able to cope with unknown situations, and is indispensable for computers to behave intelligently. We are theoretically investigating the mechanism of acquiring the generalization capability based mainly on probability and statistics.
  
  
• Development of Learning Algorithms
  Machine learning involves various subjects such as supervised learning (learning from input-output paired data), unsupervised learning (learning from input-only data), and reinforcement learning (learning through interaction with an environment). We are developing practical and theoretically motivated machine learning algorithms.
  
  
• Application of Machine Learning Technologies to Real-World
  Growth and spread of the Internet and sensor technologies allow us to collect a huge amount of data in engineering and fundamental sciences such as documents, audio, images, movies, e-commerce, electric power, medicine, and biology. We are collaborating with industry partners and applying state-of-the-art machine learning technologies to solving real-world challenging problems.

Computer Vision for Earth

Yokoya Laboratory is dedicated to addressing challenges in the acquisition and understanding of visual information based on image processing and machine learning. In particular, we focus on developing technologies for automatically constructing digital twins of the world from remote sensing data.

• Image Inverse Problem
  By integrating sensing and computation, we can obtain information that cannot be obtained from hardware alone, overcoming limitations such as resolution and noise. We are working to develop mathematical models and algorithms based on machine learning, optimization, and image processing to reconstruct original signals from incomplete observational data.
  
  
• Scene Understanding
  We are exploring methods to integrate different types of sensor data, such as optical images and LiDAR data, to comprehensively understand the semantic and 3D information of scenes with greater detail and accuracy. In addition, we are exploring approaches to build machine learning models from limited training data and improve computational efficiency.
  
  
• Remote Sensing
  With the goal of automatically constructing digital twins of the world, we are developing techniques to extract map information such as land cover and elevation models from spaceborne and airborne remote sensing data through intelligent information processing.

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.