AceChuse

Results 6 comments of AceChuse

First-order approximation

In addtion, did you try to use a large scale neural network training by a first-order approximation. Can it get a better result on dataset like miniImageNet?

First-order approximation

> > In addtion, did you try to use a large scale neural network training by a first-order approximation. Can it get a better result on dataset like miniImageNet? >...

First-order approximation

> > > > In addtion, did you try to use a large scale neural network training by a first-order approximation. Can it get a better result on dataset like...

First-order approximation

好吧，所以我才希望看到她本人来回答一下。

First-order approximation

> > 好吧，所以我才希望看到她本人来回答一下。 > > 根据李宏毅教授的讲解，他是把二阶导近似等效为0或1。但是这样对结果的精度不好。 这个有讲义资料吗？求地址啊

First-order approximation

我看到了，十分感谢！