:https://yoferzhang.gitbooks.io/machinelearningstudy/content/20170327ML04GradientDescent.html
:https://blog.csdn.net/zyq522376829/article/details/66632699
:http://ruder.io/optimizing-gradient-descent/
:https://blog.csdn.net/joshuaxx316/article/details/52062291
:https://blog.csdn.net/zhangbo_0323/article/details/77779198
:https://www.cnblogs.com/simplex/p/6671343.html
:https://blog.csdn.net/luoshixian099/article/details/51821460
:https://blog.csdn.net/qer_computerscience/article/details/55061521
:https://blog.csdn.net/linj_m/article/details/16964461