スパイク発生分子素子を利用した確率的コンピューティン物理実装とそのAI応用
| Project/Area Number |
22KJ0091
|
|---|
| Project/Area Number (Other) |
22J12918 (2022)
|
|---|
| Research Category |
Grant-in-Aid for JSPS Fellows
|
| Allocation Type | Multi-year Fund (2023)
Single-year Grants (2022) |
|---|
| Section | 国内 |
|---|
| Review Section |
Basic Section 61040:Soft computing-related
|
|---|
| Research Institution | Hokkaido University |
|---|
Principal Investigator |
KAN SHAOHUA 北海道大学, 情報科学院, 特別研究員(PD)
|
|---|
| Project Period (FY) |
2023-03-08 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2023)
|
| Budget Amount *help |
¥1,700,000 (Direct Cost: ¥1,700,000)
Fiscal Year 2023: ¥800,000 (Direct Cost: ¥800,000)
Fiscal Year 2022: ¥900,000 (Direct Cost: ¥900,000)
|
|---|
| Keywords | in-material computing / information processing / 人工知能 / 非伝統計算 / 自然物理系 |
|---|
| Outline of Research at the Start |
自然界には、その独特の材料特性やそれ自体の非線形特性のために潜在的な計算価値を持つ物理系がたくさんあります。そのため、物理系に内在する特性をどのように探索し、潜在的な計算価値を開発して適切に利用するかが重要な課題となっています。研究人は博士の期間に主に3種類の異なるデバイスを探索し、それぞれの内在特性(ランダムな電子移働、非線形な酸化還元反応、抵抗調整可能な原子ドーピングネットワーク)に基づいて3種類の異なる利用方法を設計して分類または予測機能を実現しました。
|
| Outline of Annual Research Achievements |
My research achievements were mainly did at the Nano-Electronics of the University of Twente in the Netherlands this year. I investigated information processing using atom-doped silicon-based nanodevices. By improving the output circuit, the short term memory ability is introduced into the device, and excellent results are obtained in the feature extraction of gesture video signals by applying these techniques to the processing of time signals. Based on these results, I won the Excellent Poster Award at the In-material computing workshop for young researchers hold in Sapporo.
|
Report
(2 results)
Research Products
(6 results)
