| Project/Area Number |
16K00324
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Soft computing
|
|---|
| Research Institution | Chiba University |
|---|
Principal Investigator |
Okamoto Takashi 千葉大学, グローバルプロミネント研究基幹, 特任准教授 (40451752)
|
|---|
| 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: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2017: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2016: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 大域的最適化 / システム工学 / ソフトコンピューティング / 機械学習 / 計算知能 / ニューラルネットワーク / 非線形力学 |
|---|
| Outline of Final Research Achievements |
In this research, new computational intelligence techniques fusing the optimization techniques using nonlinear dynamics and the machine learning technologies for the real applications has been developed. Specifically, a fast solver for the network routing problems using a redundant paths removing techniques and the sequential minimal optimization has been developed. Applications of the optimization techniques using the nonlinear dynamics to the deep learning have been investigated, and then, a new deep learning algorithm has been developed. A new Pareto solution visualization method using the self-organizing maps and its derived method has been developed. A new optimization techniques using the nonlinear dynamics without the parameter tuning and its parallelization have been developed. Then, the computational intelligence techniques including the developed methods in this research have been applied to the real problems; consequently, their effectiveness have been confirmed.
|
| Academic Significance and Societal Importance of the Research Achievements |
昨今，人工知能技術が大きな注目を集めているが，その根幹をなすのが，機械学習と最適化技術を中心とする計算知能技術である。本研究課題は，この計算知能技術のうち，非線形力学系を用いた最適化手法と機械学習の融合技術の開発に関するものである。また，その有用性を実問題を用いて検証しており，計算知能技術，ひいては人工知能技術の発展に資する研究成果であるといえる。
|
