The Adaptive Network Architecture for a Time-constrained Environment
-
- Demura Kosei
- Faculty of Science and Technology, Keio University
-
- Nakamura Atsushi
- Hitachi, Ltd.
-
- Anzai Yuichiro
- Faculty of Science and Technology, Keio University
Bibliographic Information
- Other Title
-
- 学習時間に制約がある環境に適したニューラルネットワーク構造学習則
Search this article
Abstract
This paper proposes an adaptive network architecture called Hybrid SOLAR (Supervised One-shot Learning Algorithm for Real number inputs), which is a hybrid algorithm between a one-shot network construction algorithm and an iterative pruning algorithm. Hybrid SOLAR determines a network structure in two stages. In the first stage, Hybrid SOLAR requires only a single presentation of training examples to construct the network and learning is finished. In the second stage, the network prunes redundant weights to improve the generalization ability. Thus, Hybrid SOLAR retains the advantages of those two algorithms. It needs only a single presentation of the training set for learning and the generalization ability is satisfactory.
Journal
-
- The Brain & Neural Networks
-
The Brain & Neural Networks 3 (2), 43-50, 1996
Japanese Neural Network Society
- Tweet
Details 詳細情報について
-
- CRID
- 1390001204466709888
-
- NII Article ID
- 10008841133
-
- NII Book ID
- AA11658570
-
- ISSN
- 18830455
- 1340766X
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed