We propose a new learning algorithm to enhance fault tolerance of multi-layer neural networks (MLN). This method is based on the idea that strong weights make MLN sensitive to faults. The purpose of new learning algorithm is to remove obstructions of fault tolerance from MLNs. We discuss about obstructions (strong connection and bias of each unit). As a result, we proposed new learning algorithm which is restricting the absolute value of weight and constructing MLNs without bias. We apply this algorithm to pattern recognition problems. It is shown that the fault tolerance of MLNs is improved.
雑誌名
Research reports of the Faculty of Engineering, Mie University
巻
25
ページ
55 - 61
発行年
2000-12-27
ISSN
0385-6208
書誌レコードID
AA00816341
フォーマット
application/pdf
著者版フラグ
publisher
その他のタイトル
Structure of Multi-layer Neural Networks for fault tolerance
階層型ニューラルネットワークの構成と耐故障性の関係
AA008163410250007.PDF
(490.39KB)
