Evolutionary computational method for artificial adaptive agents and applications
| Project/Area Number |
16K16354
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | Hiroshima University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2016: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | ニューラルネットワーク / クラシファイアシステム / 構造最適化 / エージェントベースシミュレーション / 人工適応型エージェント / 進化計算 / 機械学習 / 意思決定 / ゲーム理論 |
|---|
| Outline of Final Research Achievements |
This research results on (i)development of structural optimization method of neural network, (ii)improvement of classifier system, (iii)application corresponding to some problems in the real world. Specifically, (i) has developed an exploratory neural network structure optimization method mainly for DNN by extending the structure optimization method for neural networks. (ii) has improved some classifier systems into systems that can be used as decision-making mechanisms for artificial adaptive agents. (iii) has conducted simulation analysis on the electricity market and applications of the classification problems corresponding to the speech data using the DNN with optimized structure.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は，現実問題への応用には多くの計算コストが要求される，機械学習あるいは人工知能を主に対象としている．計算コストの削減や応用可能な問題を広げるために主に，深層学習(Deep Learning)を含めたニューラルネットワークおよびクラシファイアシステムを基礎とするシステムを開発した．本研究の成果により，計算コストを抑えることができ，例えばこれまで汎用的な計算機での実装が難しかった問題に対して，機械学習などの技術を応用可能となったと言える．
|
Report
(4 results)
Research Products
(35 results)
