Read/Search this Article
Abstract
従来, 階層型ニューラルネットワークに断線故障を注入して学習を行なうことによって, 断線故障に対し耐故障化する研究がなされている[1]-[4].本報告では, 文献[15]においてすでに報告されている単一断線故障をその特別な場合として含む結合線の単一重み故障に対する耐故障化法を, 多重重み故障の場合に拡張することについて考察する.まず, 文献[15]による方法により, 単一重み故障に対する耐故障性が得られることを再確認し, この方法を拡張することによって, 多重重み故障に対しても耐故障性が得られることを示す.次に, 耐故障性を得たネットワーク内部の様相を出力層ニューロンの入力間の共分散の分布の観点から調べ, これが耐故障化の度合と関連すること, すなわち, 耐故障性のひとつの尺度となりうることを示す.
The methods for making multi-layered neural networks fault-tolerant by injecting intentionally the snapping of a link in the learning process have been studied in the literature.However, many of them considered the fault-tolerance only to the snapping of links.This paper is an additional report on fault-tolerance for multiple weight faults of links which Takanami et al.have already reported.A simple pattern recognition problem is used as a learning object.First it is reconfirmed that fault-tolerance is obtained for the single and double weight faults.Next, it is shown that the fault tolerance for triple weight faults is also obtained.Next, the internal configuration of the network which has become fault-tolerant is analyzed by the covariance between inputs of output neurons.It is shown that the distribution of the covariances may become the measure of the degree of fault tolerance.
Journal
- Technical report of IEICE. FTS [List of Volumes]
-
Technical report of IEICE. FTS 100(30), 49-56, 2000-04-28 [Table of Contents]
The Institute of Electronics, Information and Communication Engineers