arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.15546cs.LGcs.NE
收藏

基于贝叶斯置信传播神经网络的半监督学习

Semi-supervised learning with Bayesian Confidence Propagation Neural Network

KTH Royal Institute of Technology(瑞典皇家理工学院);Stockholm University(斯德哥尔摩大学)

Naresh Balaji Ravichandran, Anders Lansner, Pawel Herman

摘要:

不使用标签或使用少量标签从数据中学习内部表示对于机器学习研究非常有用,因为它允许使用大量未标记的数据。在这项工作中,我们使用贝叶斯置信传播神经网络(BCPNN)模型开发的生物学上合理的模型的皮层。最近的工作表明,这些网络可以使用局部贝叶斯-赫布学习规则从数据中学习有用的内部表示。在这项工作中,我们将展示如何在半监督设置中,通过引入和比较不同的分类器,利用这种表示。我们还评估和比较这些网络与其他流行的半监督分类器。

英文摘要:

Learning internal representations from data using no or few labels is useful for machine learning research, as it allows using massive amounts of unlabeled data. In this work, we use the Bayesian Confidence Propagation Neural Network (BCPNN) model developed as a biologically plausible model of the cortex. Recent work has demonstrated that these networks can learn useful internal representations from data using local Bayesian-Hebbian learning rules. In this work, we show how such representations can be leveraged in a semi-supervised setting by introducing and comparing different classifiers. We also evaluate and compare such networks with other popular semi-supervised classifiers.

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。

↑