http://blog.csdn.net/u012759136/article/details/52302426 ***里面有两张动图,动图来自CS231
http://blog.csdn.net/bvl10101111/article/details/72616516
https://mp.weixin.qq.com/s/o-MFPt6LR_5XDpacqw754Q
http://ruder.io/optimizing-gradient-descent/
http://blog.csdn.net/u012759136/article/details/52302426
http://t.cj.sina.com.cn/articles/view/6105753431/16bee67570220021lu
2017年深度学习优化算法最新进展
https://baijiahao.baidu.com/s?id=1588464437869171664&wfr=spider&for=pc ***中文版
http://ruder.io/deep-learning-optimization-2017/ ***英文版
http://www.ijiandao.com/2b/baijia/63540.html ***adam
http://nnormandin.com/science/2017/07/01/yellowfin.html ***yellowFin
https://github.com/nnormandin/YellowFin_Keras ***YELLOWFIN by Keras
https://github.com/JianGoForIt/YellowFin ***YellowFin by TF
https://zhuanlan.zhihu.com/p/27648206 ****YellowFin by zhihu