Rchr
J-GLOBAL ID：201901017605851610   Update date: Sep. 06, 2024

Sato Issei

Sato Issei
Affiliation and department：
The University of Tokyo

About The University of Tokyo


Research field  (1)： Intelligent informatics
Research keywords  (1)： Machine learning
Research theme for competitive and other funds  (8)：
  • 2020 - 2025 Program Verification Techniques for the AI Era
  • 2020 - 2025 Quantifying Prediction Uncertainty in Machine Learning
  • 2017 - 2021 Learning Algorithm for Advanced Generative Models
  • 2015 - 2018 Dynamic performance improvement in computer-assisted detection system for diagnostic imaging by combined application of online learning and transfer learning
  • 2014 - 2016 Preventing A False Light Caused by k-anonymity with Mathematical Modling and Optimization
Show all
Papers (146)：
  • Soma Yokoi, Issei Sato. Top-Down Bayesian Posterior Sampling for Sum-Product Networks. 2024
  • Akiyoshi Tomihari, Issei Sato. Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective. 2024
  • Keitaro Sakamoto, Issei Sato. End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training. 2024
  • Shuo Wang, Issei Sato. Understanding Parameter Saliency via Extreme Value Theory. 2023
  • Takeshi Koshizuka, Masahiro Fujisawa, Yusuke Tanaka, Issei Sato. Initialization Bias of Fourier Neural Operator: Revisiting the Edge of Chaos. 2023
ｍore...
MISC (36)：
ｍore...
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page

TOP

BOTTOM