Scifaro

中文

卷积神经网络的 PAC-Bayesian 间隔界

机器学习 2018-04-24 v2 机器学习

作者: Konstantinos Pitas , Mike Davies , Pierre Vandergheynst

在 arXiv 上查看 ↗ PDF ↗

摘要

近来，深度神经网络的泛化误差已通过 PAC-Bayesian 框架针对全连接层的情况进行了分析。我们将此方法推广至卷积设定。

关键词

PAC-Bayesian 界泛化误差卷积神经网络深度学习

引用

@article{arxiv.1801.00171,
  title  = {PAC-Bayesian Margin Bounds for Convolutional Neural Networks},
  author = {Konstantinos Pitas and Mike Davies and Pierre Vandergheynst},
  journal= {arXiv preprint arXiv:1801.00171},
  year   = {2018}
}

备注

arXiv admin note: text overlap with arXiv:1707.09564 by other authors