> For the complete documentation index, see [llms.txt](https://luweikxy.gitbook.io/machine-learning-notes/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://luweikxy.gitbook.io/machine-learning-notes/summary.md).

# 目录

## 目录

* [封面](/machine-learning-notes/master.md)
* [目录](/machine-learning-notes/summary.md)

[机器学习算法地图](http://www.tensorinfinity.com/paper_18.html)

![machine-learning-map](/files/-LpO5wULGc9TIxxqTTC8)

## 前言

* [前言](/machine-learning-notes/perface.md)
* [个人前言](/machine-learning-notes/personal-perface.md)
* [机器学习前言](/machine-learning-notes/machine-learning-perface.md)
  * [什么是机器学习和模式识别](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vErFCmwqu-UYdpZ#什么是机器学习和模式识别)
  * [机器学习的应用](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vErFCmwqu-UYdpZ#机器学习的应用)
  * [机器学习的流程](https://luweikxy.gitbook.io/machine-learning-notes/pages/-M7qZtVZRhrsDXgrz_tb#机器学习的流程)
  * [不同机器学习算法预测效果不同](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vErFCmwqu-UYdpZ#不同机器学习算法预测效果不同)
  * [快速入门机器学习](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vErFCmwqu-UYdpZ#快速入门机器学习)
  * [机器学习需要参考哪些书](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vErFCmwqu-UYdpZ#机器学习需要参考哪些书)
  * [机器学习的学习路径](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vErFCmwqu-UYdpZ#机器学习的学习路径)
  * [深度学习的学习路径](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vErFCmwqu-UYdpZ#深度学习的学习路径)
  * [互联网机器学习特定岗位所需技能](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vErFCmwqu-UYdpZ#互联网机器学习特定岗位所需技能)
* [机器学习面试](/machine-learning-notes/interview.md)

## 数学基础

* 数学基础
* [微积分](/machine-learning-notes/calculus.md)
  * [泰勒展开](/machine-learning-notes/calculus/taylor-expansion.md)
  * [e的直观认识](/machine-learning-notes/calculus/intuition-of-e.md)
  * [傅里叶变换](/machine-learning-notes/calculus/fourier-transform.md)
  * [希尔伯特空间](/machine-learning-notes/calculus/hilbert-space.md)
* [线性代数](/machine-learning-notes/linear-algebra.md)
  * [范数](/machine-learning-notes/linear-algebra/norm.md)
  * [矩阵求导](/machine-learning-notes/linear-algebra/matrix-derivative.md)
  * [特征值](/machine-learning-notes/linear-algebra/eigenvalue.md)
  * [SVD奇异值分解](/machine-learning-notes/linear-algebra/singular-value-decomposition.md)
* [概率与信息论](/machine-learning-notes/statistics-and-information-theory.md)
  * [综述概率论基本定义](/machine-learning-notes/statistics-and-information-theory/review-of-statistics.md)
  * [概率论与贝叶斯先验](/machine-learning-notes/statistics-and-information-theory/probability-and-bayesian-prior.md)
  * [正态分布](/machine-learning-notes/statistics-and-information-theory/normal-distribution.md)
  * [贝叶斯概率](/machine-learning-notes/statistics-and-information-theory/bayes-probability.md)
  * [概率符号说明](/machine-learning-notes/statistics-and-information-theory/probability-symbol-explaination.md)
  * [共轭先验](/machine-learning-notes/statistics-and-information-theory/conjugate-prior.md)
  * [概率图模型](https://github.com/luweikxy/machine-learning-notes/tree/123475954b5254a8109117f87d962d5037609eec/content/mathematics/statistics-and-information-theory/probability-graphical-model.md)
  * [信息论](/machine-learning-notes/statistics-and-information-theory/information-theory.md)
* [数值计算与优化](/machine-learning-notes/numerical-calculation-and-optimization.md)
  * [最小二乘法](/machine-learning-notes/numerical-calculation-and-optimization/least-square-method.md)
  * [等式约束的拉格朗日乘子法](/machine-learning-notes/numerical-calculation-and-optimization/lagrangian-multiplier-method.md)
  * [凸优化](/machine-learning-notes/numerical-calculation-and-optimization/convex-optimization.md)
    * [凸集和凸函数](/machine-learning-notes/numerical-calculation-and-optimization/convex-optimization/convex-set-and-convex-function.md)
    * [凸优化问题](/machine-learning-notes/numerical-calculation-and-optimization/convex-optimization/convex-optimization-problem.md)
* [梯度下降算法](/machine-learning-notes/gradient-descent-algorithm.md)
  * [随机梯度下降SGD](/machine-learning-notes/gradient-descent-algorithm/sgd.md)
  * [动量法Momentum](/machine-learning-notes/gradient-descent-algorithm/momentum.md)
  * [牛顿动量Nesterov](/machine-learning-notes/gradient-descent-algorithm/nesterov.md)
  * [AdaGrad](/machine-learning-notes/gradient-descent-algorithm/adagrad.md)
  * [RMSprop](/machine-learning-notes/gradient-descent-algorithm/rmsprop.md)
  * [Adadelta](/machine-learning-notes/gradient-descent-algorithm/adadelta.md)
  * [Adam](/machine-learning-notes/gradient-descent-algorithm/adam.md)
  * [Nadam](/machine-learning-notes/gradient-descent-algorithm/nadam.md)
  * [AMSGrad](/machine-learning-notes/gradient-descent-algorithm/amsgrad.md)
  * [AdasMax](/machine-learning-notes/gradient-descent-algorithm/adamax.md)
* [概率图模型](/machine-learning-notes/probability-graphical-model.md)
  * [概率图模型概论](/machine-learning-notes/probability-graphical-model/probability-graphical-model-introduction.md)
  * [概率图简介](/machine-learning-notes/probability-graphical-model/probability-graph-introduction.md)

## 编程基础

* 编程基础
* [linux](/machine-learning-notes/linux.md)
  * [linux常用命令](/machine-learning-notes/linux/linux-command.md)
  * [shell](/machine-learning-notes/linux/shell.md)
    * [输入输出重定向](/machine-learning-notes/linux/shell/input_output_redirection.md)
* [python](/machine-learning-notes/python.md)
  * [python简介](/machine-learning-notes/python/introduction.md)
  * [python语法](/machine-learning-notes/python/grammar.md)
    * [基础语法](/machine-learning-notes/python/grammar/basis.md)
    * [数据结构](/machine-learning-notes/python/grammar/data-structure.md)
    * [过程控制](/machine-learning-notes/python/grammar/process-control.md)
    * [函数](/machine-learning-notes/python/grammar/function.md)
    * [类和对象](/machine-learning-notes/python/grammar/class.md)
    * [文件操作](/machine-learning-notes/python/grammar/file.md)
    * [正则表达式](/machine-learning-notes/python/grammar/regular-expression.md)
  * [python库](/machine-learning-notes/python/library.md)
    * [numpy](/machine-learning-notes/python/library/numpy.md)
    * [pandas](/machine-learning-notes/python/library/pandas.md)
    * [scipy](/machine-learning-notes/python/library/scipy.md)
    * [matplotlib](/machine-learning-notes/python/library/matplotlib.md)
    * [scikit-learn](/machine-learning-notes/python/library/scikit-learn.md)
  * [python应用](/machine-learning-notes/python/application.md)
    * [排序算法](/machine-learning-notes/python/application/sort.md)
* [数据结构与算法](/machine-learning-notes/data-structures-and-algorithms.md)
  * [数据结构](/machine-learning-notes/data-structures-and-algorithms/data-structures.md)
  * [算法思想](/machine-learning-notes/data-structures-and-algorithms/algorithms.md)
    * [排序](/machine-learning-notes/data-structures-and-algorithms/algorithms/sort.md)
      * [堆排序](/machine-learning-notes/data-structures-and-algorithms/algorithms/sort/heap-sort.md)
      * [归并排序](/machine-learning-notes/data-structures-and-algorithms/algorithms/sort/merge-sort.md)
      * [快速排序](/machine-learning-notes/data-structures-and-algorithms/algorithms/sort/quick-sort.md)
    * [递归](/machine-learning-notes/data-structures-and-algorithms/algorithms/recursion.md)
  * [剑指offer](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer.md)
    * [链表](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer/list.md)
    * [二叉树](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer/binary-tree.md)
    * [数组](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer/array.md)
    * [字符串](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer/string.md)
    * [栈和队列](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer/stack-and-queue.md)
    * [递归和回溯法](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer/recursion-and-back-tracking.md)
    * [动态规划](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer/dynamic-programming.md)
    * [其他](/machine-learning-notes/data-structures-and-algorithms/jianzhi-offer/others.md)
  * [leetcode](/machine-learning-notes/data-structures-and-algorithms/leetcode.md)
  * [编程语言](/machine-learning-notes/data-structures-and-algorithms/programming-language.md)
    * [c++](/machine-learning-notes/data-structures-and-algorithms/programming-language/c++.md)
* [Hadoop](/machine-learning-notes/hadoop.md)
  * [Hadoop简介](/machine-learning-notes/hadoop/hadoop-introduction.md)
* [MapReduce](/machine-learning-notes/hadoop/map-reduce.md)
* [Hive](/machine-learning-notes/hive.md)
* Spark
* [TensorFlow](/machine-learning-notes/tensorflow.md)
  * [TensorFlow1.0](/machine-learning-notes/tensorflow/tensorflow1.0.md)
    * [TensorFlow基础](/machine-learning-notes/tensorflow/tensorflow1.0/basis.md)
    * [TensorFlow基础概念解析](/machine-learning-notes/tensorflow/tensorflow1.0/basic-concept-analysis.md)
    * [TensorFlow机器学习基础](https://github.com/luweikxy/machine-learning-notes/tree/123475954b5254a8109117f87d962d5037609eec/content/coding/tensorflow/tensorflow1.0/machine-learning-foundation/machine-learning-foundation.md)
    * [Tensorflow分布式架构](/machine-learning-notes/tensorflow/tensorflow1.0/distributed-architecture.md)
  * [TensorFlow2.0](/machine-learning-notes/tensorflow/tensorflow2.0.md)
* [PyTorch](/machine-learning-notes/pytorch.md)

## 机器学习

* [机器学习](/machine-learning-notes/machine-learning.md)
* [机器学习概论](/machine-learning-notes/machine-learning-introduction.md)
* [特征工程](/machine-learning-notes/feature-engineering.md)
* [感知机](/machine-learning-notes/perceptron.md)
* [k近邻](/machine-learning-notes/k-nearest-neighbor.md)
* [朴素贝叶斯](/machine-learning-notes/naive-bayes.md)
* [线性模型](/machine-learning-notes/linear-model.md)
  * [最大熵模型](/machine-learning-notes/linear-model/maximum-entropy-model.md)
  * [指数族分布与广义线性模型](/machine-learning-notes/linear-model/exponential-family-distribution-and-generalized-linear-model.md)
  * [线性回归](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vGdOxgjfCd2nbHk#线性回归)
    * [Ridge回归（岭回归）](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vGdOxgjfCd2nbHk#Ridge回归（岭回归）)
    * [Lasso回归](https://luweikxy.gitbook.io/machine-learning-notes/pages/-LpO5vGdOxgjfCd2nbHk#Lasso回归)
  * [Logistic回归-对数几率回归](/machine-learning-notes/linear-model/logistic-regression.md)
* [决策树](/machine-learning-notes/decision-tree.md)
* [支持向量机](/machine-learning-notes/support-vector-machine.md)
  * [线性可分支持向量机与硬间隔最大化](/machine-learning-notes/support-vector-machine/linear-separable-svm.md)
  * [线性支持向量机与软间隔最大化](/machine-learning-notes/support-vector-machine/linear-svm.md)
  * [非线性支持向量机与核函数](/machine-learning-notes/support-vector-machine/nonlinear-svm-and-kernel-function.md)
  * [序列最小最优化算法SMO](/machine-learning-notes/support-vector-machine/smo.md)
  * [SVM总结](/machine-learning-notes/support-vector-machine/svm-summary.md)
* [集成学习](/machine-learning-notes/ensemble-learning.md)
  * Bagging
    * [随机森林](/machine-learning-notes/ensemble-learning/bagging/random-forest.md)
  * Boosting
    * [AdaBoost](/machine-learning-notes/ensemble-learning/boosting/adaboost.md)
    * GradientBoosting
      * [GBDT](/machine-learning-notes/ensemble-learning/boosting/gradientboosting/gbdt.md)
      * [XGBoost](/machine-learning-notes/ensemble-learning/boosting/gradientboosting/xgboost.md)
        * [XGBoost理论](/machine-learning-notes/ensemble-learning/boosting/gradientboosting/xgboost/xgboost-theory.md)
        * [XGBoost实践](/machine-learning-notes/ensemble-learning/boosting/gradientboosting/xgboost/xgboost-practice.md)
  * Stacking
* [降维](/machine-learning-notes/dimensionality-reduction.md)
  * [PCA主成分分析](/machine-learning-notes/dimensionality-reduction/principal-component-analysis.md)
  * [流形学习](/machine-learning-notes/dimensionality-reduction/manifold-learning.md)
* [EM算法](/machine-learning-notes/expectation-maximization-algorithm.md)
* [HMM隐马尔科夫模型](/machine-learning-notes/hidden-markov-model.md)
* [CRF条件随机场](/machine-learning-notes/conditional-random-field.md)
* [聚类](/machine-learning-notes/clustering.md)
  * [k均值聚类](/machine-learning-notes/clustering/k-means-clustering.md)
  * [高斯混合模型](/machine-learning-notes/clustering/gaussian-mixture-model.md)
* [主题模型](/machine-learning-notes/topic-model.md)
  * [LDA隐狄利克雷分布](/machine-learning-notes/topic-model/latent-dirichlet-allocation.md)
* [知识点](/machine-learning-notes/tips.md)
  * [损失函数](/machine-learning-notes/tips/loss-function.md)
  * [负采样](/machine-learning-notes/tips/negtive-sampling.md)
* [机器学习算法总结](/machine-learning-notes/machine-learning-algorithm-summary.md)

## 深度学习

* [深度学习](/machine-learning-notes/deep-learning.md)
* [深度学习概论](/machine-learning-notes/deep-learning-introduction.md)
* [ANN人工神经网络](/machine-learning-notes/artificial-neural-network.md)
* [知识点](/machine-learning-notes/tips-1.md)
  * [Batch Normalization](/machine-learning-notes/tips-1/batch-normalization.md)
* [CNN卷积神经网络](/machine-learning-notes/convolutional-neural-network.md)
* [深度学习优化算法](https://github.com/luweikxy/machine-learning-notes/tree/123475954b5254a8109117f87d962d5037609eec/content/deep-learning/deep-learning-optimization-algorithm/deep-learning-optimization-algorithm.md)
* [RNN循环神经网络](/machine-learning-notes/recurrent-neural-network.md)
* [LSTM长短期记忆网络](/machine-learning-notes/long-short-term-memory-networks.md)
* [GRU门控循环单元](/machine-learning-notes/gated-recurrent-unit.md)
* [GNN图神经网络](/machine-learning-notes/graph-neural-networks.md)
  * [GNN图神经网络综述](/machine-learning-notes/graph-neural-networks/graph-neural-networks-review.md)
  * [GCN图卷积网络](/machine-learning-notes/graph-neural-networks/graph-convolutional-networks.md)
    * [GCN图卷积网络初步理解](https://github.com/luweikxy/machine-learning-notes/tree/123475954b5254a8109117f87d962d5037609eec/content/deep-learning/graph-neural-networks/graph-convolutional-networks/gcn-preliminary-understand.md)
    * [GCN图卷积网络的numpy简单实现](https://github.com/luweikxy/machine-learning-notes/tree/123475954b5254a8109117f87d962d5037609eec/content/deep-learning/graph-neural-networks/graph-convolutional-networks/gcn-numpy-fulfillment.md)
    * [GCN图卷积网络本质理解](/machine-learning-notes/graph-neural-networks/graph-convolutional-networks/gcn-essential-understand.md)
    * [GCN图卷积网络全面理解](/machine-learning-notes/graph-neural-networks/graph-convolutional-networks/gcn-comprehensive-understand.md)
    * [SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS ICLR2017](/machine-learning-notes/graph-neural-networks/graph-convolutional-networks/semi-supervised-classification-with-graph-convolutional-networks.md)
* [神经网络架构搜索](/machine-learning-notes/neural-architecture-search.md)
  * [Weight-Agnostic-Neural-Networks Google2019](/machine-learning-notes/neural-architecture-search/weight-agnostic-neural-networks.md)

## 强化学习

* 强化学习
* [强化学习概论](/machine-learning-notes/reinforcement-learning-introduction.md)
* [马尔科夫决策过程](/machine-learning-notes/markov-decision-processes.md)
* [动态规划](/machine-learning-notes/dynamic-programming.md)
* [无模型方法一：蒙特卡洛](/machine-learning-notes/model-free-methods-1-monte-carlo.md)
* [无模型方法二：时间差分](/machine-learning-notes/model-free-methods-2-time-difference.md)
* [无模型方法三：多步自举](/machine-learning-notes/model-free-methods-3-multi-step-bootstrap.md)
* [函数近似和深度网络](/machine-learning-notes/function-approximation-and-deep-network.md)
* [策略梯度算法](/machine-learning-notes/policy-gradient-algorithm.md)
* [深度强化学习](/machine-learning-notes/deep-reinforcement-learning.md)
* [基于模型的强化学习](/machine-learning-notes/model-based-reinforcement-learning.md)
* [强化学习前景](/machine-learning-notes/reinforcement-learning-prospect.md)

## 自然语言处理

* [自然语言处理](/machine-learning-notes/natural-language-processing.md)
* [自然语言处理概论](/machine-learning-notes/natural-language-processing-introduction.md)
* [自然语言](/machine-learning-notes/natural-language.md)
* [语言模型和中文分词](/machine-learning-notes/language-model-and-chinese-word-segmentation.md)
* [word2vec](/machine-learning-notes/word2vec.md)
* [Seq2Seq模型和Attention机制](/machine-learning-notes/seq2seq-and-attention-mechanism.md)
* [Self-Attention和Transformer](/machine-learning-notes/self-attention-and-transformer.md)

## 知识图谱

* 知识图谱

## 推荐系统

* [推荐系统](/machine-learning-notes/recommender-systems.md)
* [推荐系统概述](/machine-learning-notes/recommender-systems-introduction.md)
* 基础知识
* [进阶知识](/machine-learning-notes/advanced-knowledge.md)
  * [机器学习](/machine-learning-notes/advanced-knowledge/machine-learning.md)
    * [Factorization Machines ICDM2010](/machine-learning-notes/advanced-knowledge/machine-learning/factorization-machines.md)
  * [embedding](/machine-learning-notes/advanced-knowledge/embedding.md)
    * Network Embedding
      * [LINE: Large-scale Information Network Embedding](/machine-learning-notes/advanced-knowledge/embedding/network-embedding/line-large-scale-information-network-embedding.md)
  * [深度学习](/machine-learning-notes/advanced-knowledge/deep-learning.md)
    * [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction 2017](/machine-learning-notes/advanced-knowledge/deep-learning/deepfm-a-factorization-machine-based-neural-network-for-ctr-prediction.md)
    * [DSSM: Learning Deep Structured Semantic Models for Web Search using Clickthrough Data CIKM2013](/machine-learning-notes/advanced-knowledge/deep-learning/learning-deep-structured-semantic-models-for-web-search-using-clickthrough-data.md)
  * [图卷积网络](/machine-learning-notes/advanced-knowledge/graph-convolutional-network.md)
    * [Graph Convolutional Neural Networks for Web-Scale Recommender Systems KDD2018](/machine-learning-notes/advanced-knowledge/graph-convolutional-network/graph-convolutional-neural-networks-for-web-scale-recommender-systems.md)
  * [强化学习](/machine-learning-notes/advanced-knowledge/reinforcement-learning.md)
    * [DRN基于深度强化学习的新闻推荐模型](/machine-learning-notes/advanced-knowledge/reinforcement-learning/drn-a-deep-reinforcement-learning-framework-for-news-recommendation.md)
* [业界应用](/machine-learning-notes/industry-application.md)
  * [YouTube](https://github.com/luweikxy/machine-learning-notes/tree/123475954b5254a8109117f87d962d5037609eec/content/recommender-systems/industry-application/youtube/youtube.md)
    * [Deep Neural Networks for YouTube Recommendations RecSys2016](https://github.com/luweikxy/machine-learning-notes/tree/123475954b5254a8109117f87d962d5037609eec/content/recommender-systems/industry-application/youtube/deep-neural-networks/Deep-Neural-Networks-for-YouTube-Recommendations.md)
  * [Alibaba](/machine-learning-notes/industry-application/alibaba.md)
    * [Learning Tree-based Deep Model for Recommender Systems KDD2018](/machine-learning-notes/industry-application/alibaba/learning-tree-based-deep-model-for-recommender-systems.md)
    * [Deep Interest Network for Click-Through Rate Prediction KDD2018](/machine-learning-notes/industry-application/alibaba/deep-interest-network-for-click-through-rate-prediction.md)
    * [DSIN:Deep Session Interest Network for Click-Through Rate Prediction IJCAI2019](/machine-learning-notes/industry-application/alibaba/dsin-deep-session-interest-network-for-click-through-rate-prediction.md)