|
Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >
An incremental self-organizing neural network based on enhanced competitive Hebbian learning
| Title: | An incremental self-organizing neural network based on enhanced competitive Hebbian learning |
| Authors: | Liu, Hao Browse this author | | Kurihara, Masahito Browse this author →KAKEN DB | | Oyama, Satoshi Browse this author →KAKEN DB | | Sato, Haruhiko Browse this author →KAKEN DB |
| Issue Date: | 2013 |
| Publisher: | IEEE (Institute of Electrical and Electronics Engineers) |
| Citation: | The 2013 International Joint Conference on Neural Networks (IJCNN), ISBN: 978-1-4673-6129-3 |
| Start Page: | 1 |
| End Page: | 8 |
| Publisher DOI: | 10.1109/IJCNN.2013.6706725 |
| Abstract: | Self-organizing neural networks are important tools for realizing unsupervised learning. Recently, a difficult task has involved the incremental, efficient and robust learning in noisy environments. Most of the existing techniques are poor in this regard. In this paper, we first propose a new topology generating method called enhanced competitive Hebbian learning (enhanced CHL), and then propose a novel incremental self-organizing neural network based on the enhanced CHL method, called enhanced incremental growing neural gas (Hi- GNG). The experiments presented in this paper show that the Hi-GNG algorithm can automatically and efficiently generate a topological structure with a suitable number of neurons and that the proposed algorithm is robust to noisy data. |
| Conference Name: | IEEE International Joint Conference on Neural Networks (IJCNN) |
| Conference Sequence: | 2013 |
| Conference Place: | Dallas, Texas |
| Rights: | © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| Type: | proceedings (author version) |
| URI: | http://hdl.handle.net/2115/65582 |
| Appears in Collections: | 情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
Submitter: 小山 聡
|
