Multi-Branch Structure and its Localized Property in Layered Neural Networks
-
- Yamashita Takashi
- Graduate School of Information, Production and Systems, Waseda University
-
- Hirasawa Kotaro
- Graduate School of Information, Production and Systems, Waseda University
-
- Furuzuki Takayuki
- Graduate School of Information, Production and Systems, Waseda University
Bibliographic Information
- Other Title
-
- 階層型ニューラルネットワークにおけるマルチブランチ構造とその局所性
- カイソウガタ ニューラル ネットワーク ニ オケル マルチブランチ コウゾウ ト ソノ キョクショセイ
Search this article
Abstract
Neural networks (NNs) can solve only a simple problem if the network size is too small, on the other hand, if the network size increases, it costs a lot in terms of memory space and calculation time. So, we have studied how to construct the network structure with high performances and low costs in space and time. A solution is a multi-branch structure. Conventional NNs use the single-branch for the connections, while the multi-branch structure has multi-branches between nodes. In this paper, a new method which enables the multi-branch NNs to have localized property is proposed. It is well known that RBF networks have localized property that makes it possible to approximate functions faster than sigmoidal NNs. By using the multi-branch structure having localized property of RBF networks, NNs could obtain high performances keeping the lower costs in space and time. Simulation results of function approximations and a classification problem illustrated the effectiveness of multi-branch NNs.
Journal
-
- IEEJ Transactions on Electronics, Information and Systems
-
IEEJ Transactions on Electronics, Information and Systems 125 (6), 941-947, 2005
The Institute of Electrical Engineers of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390001204606257024
-
- NII Article ID
- 10015672231
-
- NII Book ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL BIB ID
- 7387835
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed