copy and paste this google map to your website or blog!
Press copy button and paste into your blog or website.
(Please switch to 'HTML' mode when posting into your blog. Examples: WordPress Example, Blogger Example)
如何理解 natural gradient descent? - 知乎 看到一篇文章写得非常浅显易懂: What is the natural gradient, and how does it work? 总结一下: 拿神经网络中的反向传播算法举例,我们计算各个权值w关于损失函数的导数,得到一个梯度向量,然后沿着这个梯度的反方向更新权值一小段距离,如此不断重复来使损失函数收敛到(局部)最小值。 问题就在于
梯度消失问题为什么不通过 gradient scaling 来解决? - 知乎 The truth is, once your gradient results've already too slight to be distinguished from other noise-disturbances, you scale up all the observable vibrations, you still cannot distinguish the correct gradient signals from noises