PAC-Bayesian Margin Bounds for Convolutional Neural Networks - Technical Report.
arXiv: Learning(2018)
摘要
Recently the generalisation error of deep neural networks has been analysed through the PAC-Bayesian framework, for the case of fully connected layers. We adapt this approach to the convolutional setting.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络