数学系学术讲座(十三)

题  目：Stochastic Second-Order Methods For Deep Learning内容简介：Stochastic Stochastic methods are widely used in deep learning. In this talk, we first review the state-of-the-art methods such as KFAC. Then we present a structured stochastic quasi-Newton method and a sketchy empirical natural gradient method. Numerical results on deep convolution networks illustrate that our methods are qui...

2020-12-07

地址：广州市黄埔大道西601号 暨南大学（邮编：510632)

联系电话：

电子邮箱：oxky@jnu.edu.cn

版权所有 © 暨南大学信息科学技术学院 粤ICP备12087612号

学院团委微信平台

扫一扫关注学院