arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.07068cs.LG
收藏

一种新的随机结构网络学习范式:SCN +

A New Learning Paradigm for Stochastic Configuration Network: SCN+

China University of Mining and Technology(中国矿业大学);Northeastern University(东北大学)

Yanshuang Ao, Xinyu Zhou, Wei Dai

摘要:

特权信息学习(LUPI)范式开创了师生互动机制,使学习模型在训练阶段使用额外信息。首次提出了一种基于LUPI范式的随机构形网络增量式学习算法SCN+。该算法能够在训练阶段将优先权信息引入到SCN中,为训练SCN提供了一种新的方法。此外,本文还研究了算法的收敛性。最后,实验结果表明,SCN+确实表现良好。

英文摘要:

Learning using privileged information (LUPI) paradigm, which pioneered teacher-student interaction mechanism, makes the learning models use additional information in training stage. This paper is the first to propose an incremental learning algorithm with LUPI paradigm for stochastic configuration network (SCN), named SCN+. This novel algorithm can leverage privileged information into SCN in the training stage, which provides a new method to train SCN. Moreover, the convergences have been studied in this paper. Finally, experimental results indicate that SCN+ indeed performs favorably.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑