Neural Networks with Input Gates
-
- Murata Junichi
- Department of Electrical and Electronic Systems Engineering, Kyushu University
-
- Noda Tetsushi
- Faculty of Engineering Sciences : Master's Program
-
- Hirasawa Kotaro
- Department of Electrical and Electronic Systems Engineering, Kyushu University
Bibliographic Information
- Other Title
-
- 入力ゲート付きニューラルネットワーク
Search this article
Abstract
An architecture of multi layer neural networks is proposed. The networks are equipped with gates on their input channels to control flow of the input signals. A gate on an input channel opens and closes depending on the current values of the other input signals. The dependency is automatically determined based on training data so that the gate opens when the corresponding input is necessary arid closed when not necessary. These gates give the networks a good generalization ability because they can eliminate harmful inputs. And they provides us with an insight into the input-output relationship since they can indicate which input is significant in what situation.
Journal
-
- 九州大学大学院システム情報科学紀要
-
九州大学大学院システム情報科学紀要 2 (2), 283-288, 1997-09-26
Graduate School of Information Science and Electrical Engineering, Kyushu University
- Tweet
Details 詳細情報について
-
- CRID
- 1390853649773730944
-
- NII Article ID
- 110000579862
-
- NII Book ID
- AN10569524
-
- DOI
- 10.15017/1524284
-
- ISSN
- 21880891
- 13423819
-
- HANDLE
- 2324/1524284
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- IRDB
- CiNii Articles
-
- Abstract License Flag
- Allowed