| 研究課題/領域番号 |
20H04249
|
|---|
| 研究種目 |
基盤研究(B)
|
| 配分区分 | 補助金 |
|---|
| 応募区分 | 一般 |
|---|
| 審査区分 |
小区分61030:知能情報学関連
|
|---|
| 研究機関 | 国立研究開発法人理化学研究所 |
|---|
研究代表者 |
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)
|
|---|
| 研究分担者 |
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)
|
|---|
| 研究期間 (年度) |
2020-04-01 – 2024-03-31
|
| 研究課題ステータス |
完了 (2023年度)
|
| 配分額 *注記 |
17,550千円 (直接経費: 13,500千円、間接経費: 4,050千円)
2023年度: 4,290千円 (直接経費: 3,300千円、間接経費: 990千円)
2022年度: 4,290千円 (直接経費: 3,300千円、間接経費: 990千円)
2021年度: 4,290千円 (直接経費: 3,300千円、間接経費: 990千円)
2020年度: 4,680千円 (直接経費: 3,600千円、間接経費: 1,080千円)
|
|---|
| キーワード | tensor network / tensor decomposition / adversarial robustness / Tensor networks / machine learning / tensor networks / Tensor Networks / Machine Learning / Robustness |
|---|
| 研究開始時の研究の概要 |
Tensor networks (TNs) have recently gained increasing attentions in machine learning, data mining and computer vision fields due to its effectiveness in efficient computation and model compression in deep learning. However, there are many open problems that are still unexplored, which limits its impact in machine learning. Therefore, our research aims to investigate the fundamental theory and develop scalable and efficient learning algorithms for TN. Moreover, we will further explore what challenging problems in machine learning can be solved by TN technology.
|
| 研究実績の概要 |
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.
|
| 現在までの達成度 (段落) |
令和5年度が最終年度であるため、記入しない。
|
| 今後の研究の推進方策 |
令和5年度が最終年度であるため、記入しない。
|
