| Project/Area Number |
16K00246
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Future University-Hakodate |
|---|
Principal Investigator |
Katori Yuichi 公立はこだて未来大学, システム情報科学部, 准教授 (20557607)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 非線形ダイナミクス / 脳型人工知能 / リザバー計算 / 時系列解析 / 聴覚情報処理 / ニューラルネットワーク / レザバー計算 / 多変量解析 / 脳波 / リザーバ計算 / スパース性 / 機械学習 / 音声等認識 |
|---|
| Outline of Final Research Achievements |
We conducted on establishing a modeling principle applicable to multidimensional time-series data assuming auditory data based on the framework of reservoir computing that performs various information processing using complex motion that occurs in a coupled system of many nonlinear elements. The network model based on reservoir computing and predictive coding is extended to a hierarchical network. We evaluated the performance of the proposed model using acoustic data and succeeded in extracting the hierarchical structure of acoustic time series data. In the process of research, we found that it could be applied not only to speech and sound but also to various objects and developed research in multiple ways. It could be developed into various applied research such as a model of the visual system, analysis of multivariate time series data, and robot control.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は高次元の非線形力学系で生じる複雑なダイナミクスを積極的に活用することで，新しい情報処理の仕組みを構築する試みである．本研究の成果は，音声・音響だけでなく視覚的な情報，各種センサー情報処理，ロボット制御などを含む，新しい脳型人工知能など工学的な応用に結びつくことが強く期待される．また非線形素子の結合系ともみなせる生体の脳・神経ネットワークの情報処理機構の理解を通して，生理学・医学の発展に結びつくことが期待できる．
|
