https://github.com/tsycnh/mlbasic
深度学习常用优化方法详解
https://github.com/tsycnh/mlbasic
gradient-descent minibatch-sgd momentum sgd
Last synced: 4 months ago
JSON representation
深度学习常用优化方法详解
- Host: GitHub
- URL: https://github.com/tsycnh/mlbasic
- Owner: tsycnh
- Created: 2017-07-14T02:23:48.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-07-22T05:13:52.000Z (about 8 years ago)
- Last Synced: 2025-06-01T11:45:03.686Z (4 months ago)
- Topics: gradient-descent, minibatch-sgd, momentum, sgd
- Language: Python
- Homepage:
- Size: 20.5 KB
- Stars: 268
- Watchers: 10
- Forks: 100
- Open Issues: 1
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
# 一些关于机器学习优化函数的练习
* p1: 最基本的梯度下降法:gradient descent
* p2: 原始 SGD方法:stochastic gradient descent
* p3: minibatch-SGD方法
* p4 momentum SGD: minibatch-SGD with momentum
* p4 momentum: momentum with SGD
* p5: Nesterov方法
* p6: adagrad
* p7: adadelta
* p8: adam#### 参考
p1 参考 https://zhuanlan.zhihu.com/p/27297638p2~pn 参考 http://ruder.io/optimizing-gradient-descent/index.html
###### 单独参考
p5 参考 http://cs231n.github.io/neural-networks-3/
p6 参考 https://zhuanlan.zhihu.com/p/22252270
p7 参考 https://arxiv.org/abs/1212.5701 (原始论文)
p8 参考 http://www.ijiandao.com/2b/baijia/63540.html