2023 Fiscal Year Annual Research Report
Tensor Network Representation for Machine Learning: Theoretical Study and Algorithms Development
| Project/Area Number |
20H04249
|
|---|
| Research Institution | Institute of Physical and Chemical Research |
|---|
Principal Investigator |
ZHAO QIBIN 国立研究開発法人理化学研究所, 革新知能統合研究センター, チームリーダー (30599618)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
曹 建庭 埼玉工業大学, 工学部, 教授 (20306989)
横田 達也 名古屋工業大学, 工学(系)研究科(研究院), 准教授 (80733964)
|
|---|
| Project Period (FY) |
2020-04-01 – 2024-03-31
|
| Keywords | tensor network / tensor decomposition / adversarial robustness |
|---|
| Outline of Annual Research Achievements |
In this fiscal year, we further studied how to learn an optimal tensor network structure efficiently, and developed a fast algorithm for solving it. Then, we applied these algorithms to tensor completion task.
We have also studied nonlinear tensor decomposition methods for handling more complex data tensor. A scalable Bayesian tensor ring factorization, undirected probabilistic model for tensor decomposition, and efficient nonparametric tensor decomposition approaches are developed and evaluated on many datasets.
We also studied the adversarial robustness of neural networks by using tensorized parameterization. In addition, we studied how to perform adversarial purification more effectively by using adversarial loss.
|
| Research Progress Status |
令和5年度が最終年度であるため、記入しない。
|
| Strategy for Future Research Activity |
令和5年度が最終年度であるため、記入しない。
|
