| Project/Area Number |
22K17960
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | National Institute of Advanced Industrial Science and Technology |
|---|
Principal Investigator |
SALESDESOUZA LINCON 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究員 (40912481)
|
|---|
| Project Period (FY) |
2022-04-01 – 2026-03-31
|
| Project Status |
Granted (Fiscal Year 2024)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2025: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2024: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2023: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2022: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | subspace learning / deep neural networks / Subspace learning / Deep neural networks / Manifold optimization / Subspace methods / Pattern recognition |
|---|
| Outline of Research at the Start |
We research a new algorithm for pattern recognition, which are computer programs that allow a machine to automatically recognize regularities in data, such as target objects and events. We mainly focus on the case of recognizing patterns in given multiple images of one object, addressing some inabilities of the current technology called deep learning.
|
| Outline of Annual Research Achievements |
In year 2024, we continued working on the combination of neural networks and subspace learning. We have worked in an application to environmental sound classification, where we propose a method using an ensemble of subspace representations of latent features obtained from various neural network-based models. We were able to successfully achieve a competitive performance on real data, and published this result on the journal Applied Acoustics. We also developed a method for data analysis in a Riemannian geometry. We specifically proposed a time-series data embedding technique that preserves manifold curvature and orientation. We showcased our method in a setting with subspace representation, with an use case of analyzing the temporal information encoded in neural activation dynamics.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
We have been able apply our methods to environmental sound classification, and to develop a manifold data analysis method and apply to analyze neural data.
|
| Strategy for Future Research Activity |
We conclude the research project by finishing all the experiments and submitting the remaining work.
|
