XCSR Learning from Compressed Data Acquired by Deep Neural Network
-
- Matsumoto Kazuma
- The University of Electro-Communications
-
- Tatsumi Takato
- The University of Electro-Communications
-
- Sato Hiroyuki
- The University of Electro-Communications
-
- Kovacs Tim
- The University of Bristol
-
- Takadama Keiki
- The University of Electro-Communications
Search this article
Abstract
<p>The correctness rate of classification of neural networks is improved by deep learning, which is machine learning of neural networks, and its accuracy is higher than the human brain in some fields. This paper proposes the hybrid system of the neural network and the Learning Classifier System (LCS). LCS is evolutionary rule-based machine learning using reinforcement learning. To increase the correctness rate of classification, we combine the neural network and the LCS. This paper conducted benchmark experiments to verify the proposed system. The experiment revealed that: 1) the correctness rate of classification of the proposed system is higher than the conventional LCS (XCSR) and normal neural network; and 2) the covering mechanism of XCSR raises the correctness rate of proposed system.</p>
Journal
-
- Journal of Advanced Computational Intelligence and Intelligent Informatics
-
Journal of Advanced Computational Intelligence and Intelligent Informatics 21 (5), 856-867, 2017-09-20
Fuji Technology Press Ltd.
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282763070054528
-
- NII Article ID
- 130007520187
-
- NII Book ID
- AA12042502
-
- ISSN
- 18838014
- 13430130
-
- NDL BIB ID
- 028510831
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed