Skip to main navigation Skip to search Skip to main content

前馈网的知识扩充及故障恢复

Translated title of the contribution: Knowledge extension and fault recovery of feed-forward neural networks

石俊, 陈幼平, Peter Wai-Tat Tse

    Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

    Abstract

    Aiming at the problem of poor extensibility of feed-forward neural networks, a knowledge extension method is proposed in this paper. Preserving the original neural networks, we can both retain existing training result and learn new knowledge by adding a new subnet. Simultaneously, the strategy of fault recovery of neural networks is studied and a fault compensation algorithm is given. The effectiveness of proposed algorithms is verified by numerical simulations.
    Translated title of the contributionKnowledge extension and fault recovery of feed-forward neural networks
    Original languageChinese (Simplified)
    Pages (from-to)189-192
    Journal控制理论与应用/Control Theory & Applications
    Volume17
    Issue number2
    Publication statusPublished - Apr 2000

    Research Keywords

    • 前馈网
    • 学习
    • 故障补偿
    • FNN
    • Learning
    • Fault compensation

    Fingerprint

    Dive into the research topics of 'Knowledge extension and fault recovery of feed-forward neural networks'. Together they form a unique fingerprint.

    Cite this