lishanian / machine-learning-notes

机器学习笔记

简介

作者：hschen
QQ：357033150
邮箱：[e-mail]

此笔记主要总结自一些论文、书籍以及公开课，由于本人水平有限，笔记中难免会出现各种错误，欢迎指正。
由于Github渲染.ipynb文件较慢，可以用nbviewer加快渲染：点此加速

目录

1.CS229课程笔记

• 广义线性模型
• 增强学习系列1
• 增强学习系列2

2.PRML读书笔记

• 第一章 简介
  • 1.1 多项式曲线拟合
  • 1.2 概率论回顾
  • 总结-曲线拟合的三种参数估计方法
• 第二章 概率分布
  • 2.1 二元变量
  • 2.2 多元变量
• 第三章 线性回归模型
  • 总结-贝叶斯线性回归

3.[徐亦达机器学习笔记](YiDaXu ML/)

• [采样算法系列1](YiDaXu ML/sampling-methods-part1.ipynb)
• [EM算法](YiDaXu ML/EM-review.ipynb)
• [变分推断](YiDaXu ML/variational-inference.ipynb)
• [高斯分布的变分推断](YiDaXu ML/variational-inference-for-gaussian-distribution.ipynb)
• [指数分布族](YiDaXu ML/exponential-family.ipynb)
• [指数分布族的变分推断](YiDaXu ML/exponential-family-variational-inference.ipynb)

4.[机器学习笔记](Machine Learning/)

• [xgboost笔记](Machine Learning/xgboost-notes)
  • [1. xgboost的安装](Machine Learning/xgboost-notes/xgboost-note1.ipynb)
• [softmax分类器](Machine Learning/softmax-crossentropy-derivative.ipynb)
• [用theano实现softmax分类器](Machine Learning/implement-softmax-in-theano.ipynb)
• [用SVD实现岭回归](Machine Learning/svd-ridge-regression.ipynb)
• [SVD系列1](Machine Learning/svd1.ipynb)

5.[深度学习笔记](Deep Learning/)

• [theano笔记](Deep Learning/theano-notes)

  • [2. theano简单计算](Deep Learning/theano-notes/part2-simple-computations.ipynb)
  • [3. theano共享变量](Deep Learning/theano-notes/part3-shared-variable.ipynb)
  • [4. theano随机数](Deep Learning/theano-notes/part4-random-number.ipynb)
  • [6. theano的scan函数](Deep Learning/theano-notes/part6-scan-function.ipynb)
  • [7. theano的dimshuffle](Deep Learning/theano-notes/part7-dimshuffle.ipynb)

• [mxnet笔记](Deep Learning/mxnet-notes)

  • [1. Win10下安装MXNET](Deep Learning/mxnet-notes/1-installation.ipynb)
  • [2. MXNET符号API](Deep Learning/mxnet-notes/2-mxnet-symbolic.ipynb)
  • [mxnet中的运算符](Deep Learning/mxnet-notes/operators-in-mxnet.ipynb)
  • [mshadow表达式模板教程](Deep Learning/mxnet-notes/mshadow-expression-template-tutorial.ipynb)

• [keras笔记](Deep Learning/keras-notes)

  • [keras心得](Deep Learning/keras-notes/keras-tips.ipynb)

• [windows下安装caffe](Deep Learning/install-caffe-in-windows.ipynb)

• [BP算法矩阵形式推导](Deep Learning/back-propagation-in-matrix-form.ipynb)

• [随时间反向传播算法数学推导过程](Deep Learning/back-propagation-through-time.ipynb)

• [用numpy实现RNN](Deep Learning/rnn-numpy.ipynb)

• [随机矩阵的奇异值分析](Deep Learning/singular-value-of-random-matrix.ipynb)