paper: How Many Samples are Needed to Estimate a Convolutional Neural Network?

Abstract:
more compact representation ==> less sample

SRE实战 互联网时代守护先锋，助力企业售后服务体系运筹帷幄！一键直达领取阿里云限量特价优惠。

generalization bound 不是基于 model capacity 的，令人耳目一新。

重点截图

留待处理的疑难点

NIPS2018-How Many Samples are Needed to Estimate a Convolutional Neural Network? 随笔

扫码关注我们
微信号：SRE实战
拒绝背锅 运筹帷幄