Self Evolving Modular Network
Summary :
We propose a novel modular network called the Self-Evolving Modular Network (SEEM). The SEEM has a modular network architecture with a graph structure and these following advantages: (1) new modules are added incrementally to allow the network to adapt in a self-organizing manner, and (2) graph's paths are formed based on the relationships between the models represented by modules. The SEEM is expected to be applicable to evolving functions of an autonomous robot in a self-organizing manner through interaction with the robot's environment and categorizing large-scale information. This paper presents the architecture and an algorithm for the SEEM. Moreover, performance characteristic and effectiveness of the network are shown by simulations using cubic functions and a set of 3D-objects.
- Publication
- IEICE TRANSACTIONS on Information Vol.E95-D No.5 pp.1506-1518
- Publication Date
- 2012/05/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E95.D.1506
- Type of Manuscript
- PAPER
- Category
- Biocybernetics, Neurocomputing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kazuhiro TOKUNAGA, Nobuyuki KAWABATA, Tetsuo FURUKAWA, "Self Evolving Modular Network" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 5, pp. 1506-1518, May 2012, doi: 10.1587/transinf.E95.D.1506.
Abstract: We propose a novel modular network called the Self-Evolving Modular Network (SEEM). The SEEM has a modular network architecture with a graph structure and these following advantages: (1) new modules are added incrementally to allow the network to adapt in a self-organizing manner, and (2) graph's paths are formed based on the relationships between the models represented by modules. The SEEM is expected to be applicable to evolving functions of an autonomous robot in a self-organizing manner through interaction with the robot's environment and categorizing large-scale information. This paper presents the architecture and an algorithm for the SEEM. Moreover, performance characteristic and effectiveness of the network are shown by simulations using cubic functions and a set of 3D-objects.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.1506/_p
Copy
@ARTICLE{e95-d_5_1506,
author={Kazuhiro TOKUNAGA, Nobuyuki KAWABATA, Tetsuo FURUKAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Self Evolving Modular Network},
year={2012},
volume={E95-D},
number={5},
pages={1506-1518},
abstract={We propose a novel modular network called the Self-Evolving Modular Network (SEEM). The SEEM has a modular network architecture with a graph structure and these following advantages: (1) new modules are added incrementally to allow the network to adapt in a self-organizing manner, and (2) graph's paths are formed based on the relationships between the models represented by modules. The SEEM is expected to be applicable to evolving functions of an autonomous robot in a self-organizing manner through interaction with the robot's environment and categorizing large-scale information. This paper presents the architecture and an algorithm for the SEEM. Moreover, performance characteristic and effectiveness of the network are shown by simulations using cubic functions and a set of 3D-objects.},
keywords={},
doi={10.1587/transinf.E95.D.1506},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Self Evolving Modular Network
T2 - IEICE TRANSACTIONS on Information
SP - 1506
EP - 1518
AU - Kazuhiro TOKUNAGA
AU - Nobuyuki KAWABATA
AU - Tetsuo FURUKAWA
PY - 2012
DO - 10.1587/transinf.E95.D.1506
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2012
AB - We propose a novel modular network called the Self-Evolving Modular Network (SEEM). The SEEM has a modular network architecture with a graph structure and these following advantages: (1) new modules are added incrementally to allow the network to adapt in a self-organizing manner, and (2) graph's paths are formed based on the relationships between the models represented by modules. The SEEM is expected to be applicable to evolving functions of an autonomous robot in a self-organizing manner through interaction with the robot's environment and categorizing large-scale information. This paper presents the architecture and an algorithm for the SEEM. Moreover, performance characteristic and effectiveness of the network are shown by simulations using cubic functions and a set of 3D-objects.
ER -
English
