ApacheCN 人工智能知识树 v1.0

骑猪看日落 2022-01-30 05:51 184阅读 0赞

> Special Sponsors

[![CodingNet.png][]][CodingNet.png 1]

> 贡献者：[飞龙][Link 1]
> 
> 版本：v1.0

最近总是有人问我，把 ApacheCN 这些资料看完一遍要用多长时间，如果你一本书一本书看的话，的确要用很长时间。但我觉得这是非常麻烦的，因为每本书的内容大部分是重复的，有些不重复的内容你也不好找。为了方便大家，我就把每本书的章节拆开，再按照知识点合并，手动整理了这个知识树。大家可以按照知识点依次学习，如果理解了一个知识点，就没必要看其余文章，直接跳到下一个就行了。

## 统计机器学习 ##

### 基础知识 ###

*  [AILearning 第1章\_基础知识][AILearning _1]
 *  [CS229 中文笔记 一、引言][CS229 _]
 *  [CS229 中文笔记 三、线性代数回顾][CS229 _]
 *  [机器学习基石 1 – The Learning Problem][1 _ The Learning Problem]
 *  [机器学习基石 2 – Learning to Answer Yes/No][2 _ Learning to Answer Yes_No]
 *  [机器学习基石 3 – Types of Learning][3 _ Types of Learning]
 *  [机器学习基石 4 – Feasibility of Learning][4 _ Feasibility of Learning]
 *  [机器学习基石 6 – Theory of Generalization][6 _ Theory of Generalization]
 *  [机器学习基石 7 – The VC Dimension][7 _ The VC Dimension]
 *  [机器学习基石 8 – Noise and Error][8 _ Noise and Error]
 *  [机器学习基石 16 – Three Learning Principles][16 _ Three Learning Principles]
 *  [写给人类的机器学习 一、为什么机器学习重要][Link 2]
 *  [SciPyCon 2018 sklearn 教程 一、Python 机器学习简介][SciPyCon 2018 sklearn _ _Python]
 *  [SciPyCon 2018 sklearn 教程 二、Python 中的科学计算工具][SciPyCon 2018 sklearn _ _Python 1]
 *  [SciPyCon 2018 sklearn 教程 九、sklearn 估计器接口回顾][SciPyCon 2018 sklearn _ _sklearn]
 *  [SciPyCon 2018 sklearn 教程 十五、估计器流水线][SciPyCon 2018 sklearn _]
 *  [数据科学和人工智能技术笔记 一、向量、矩阵和数组][Link 3]
 *  [Sklearn 学习指南 第一章：机器学习 - 温和的介绍][Sklearn _ _ -]

### 线性回归/逻辑回归/softmax 回归 ###

*  [AILearning 第5章\_逻辑回归][AILearning _5]
 *  [AILearning 第8章\_回归][AILearning _8]
 *  [CS229 中文笔记 二、单变量线性回归][CS229 _]
 *  [CS229 中文笔记 四、多变量线性回归][CS229 _ 1]
 *  [CS229 中文笔记 六、逻辑回归][CS229 _ 1]
 *  [DLAI 深度学习笔记 第一门课 第二周：神经网络的编程基础][DLAI _ _]
 *  [机器学习基石 9 – Linear Regression][9 _ Linear Regression]
 *  [机器学习基石 10 – Logistic Regression][10 _ Logistic Regression]
 *  [机器学习基石 11 – Linear Models for Classification][11 _ Linear Models for Classification]

*  [机器学习基石 12 – Nonlinear Transformation][12 _ Nonlinear Transformation]

*  [机器学习技法 5 – Kernel Logistic Regression][5 _ Kernel Logistic Regression]
 *  [Scikit-learn 秘籍 第二章 处理线性模型][Scikit-learn _ _]
 *  [Scikit-learn 秘籍 第四章 使用 scikit-learn 对数据分类][Scikit-learn _ _ _ scikit-learn]
 *  [PythonProgramming.net 系列教程 第一部分 回归][PythonProgramming.net _ _]
 *  [写给人类的机器学习 2.1 监督学习][2.1]
 *  [写给人类的机器学习 2.2 监督学习 II][2.2 _ II]
 *  [Python 数据分析与挖掘实战 第5章　挖掘建模][Python _ _5]
 *  [Python 数据分析与挖掘实战 第13章　财政收入影响因素分析及预测模型][Python _ _13]
 *  [与 TensorFlow 的初次接触 2. TensorFlow 中的线性回归][TensorFlow _ 2. TensorFlow]
 *  [SciPyCon 2018 sklearn 教程 五、监督学习第一部分：分类][SciPyCon 2018 sklearn _ 1]
 *  [SciPyCon 2018 sklearn 教程 六、监督学习第二部分：回归分析][SciPyCon 2018 sklearn _ 2]
 *  [SciPyCon 2018 sklearn 教程 十七、深入：线性模型][SciPyCon 2018 sklearn _ 3]
 *  [数据科学和人工智能技术笔记 十一、线性回归][Link 4]
 *  [数据科学和人工智能技术笔记 十二、逻辑回归][Link 5]
 *  [Sklearn 学习指南 第二章：监督学习][Sklearn _]

### 决策树/随机森林 ###

*  [AILearning 第3章\_决策树算法][AILearning _3]
 *  [AILearning 第9章\_树回归][AILearning _9]
 *  [机器学习技法 9 – Decision Tree][9 _ Decision Tree]
 *  [机器学习技法 10 – Random Forest][10 _ Random Forest]
 *  [Scikit-learn 秘籍 第四章 使用 scikit-learn 对数据分类][Scikit-learn _ _ _ scikit-learn]
 *  [写给人类的机器学习 2.3 监督学习 III][2.3 _ III]
 *  [Python 数据分析与挖掘实战 第5章　挖掘建模][Python _ _5]
 *  [Python 数据分析与挖掘实战 第6章　电力窃漏电用户自动识别][Python _ _6]
 *  [SciPyCon 2018 sklearn 教程 十八、深入：决策树与森林][SciPyCon 2018 sklearn _ 4]
 *  [数据科学和人工智能技术笔记 十三、树和森林][Link 6]
 *  [Sklearn 学习指南 第二章：监督学习][Sklearn _]

### GDBT/XGBoost ###

*  [机器学习技法 11 – Gradient Boosted Decision Tree][11 _ Gradient Boosted Decision Tree]

### 朴素贝叶斯 ###

*  [AILearning 第4章\_朴素贝叶斯][AILearning _4]
 *  [Scikit-learn 秘籍 第四章 使用 scikit-learn 对数据分类][Scikit-learn _ _ _ scikit-learn]
 *  [数据科学和人工智能技术笔记 十六、朴素贝叶斯][Link 7]
 *  [Sklearn 学习指南 第二章：监督学习][Sklearn _]

### 支持向量机 ###

*  [AILearning 第6章\_支持向量机][AILearning _6]
 *  [AILearning 支持向量机的几个通俗理解][AILearning]
 *  [CS229 中文笔记 十二、支持向量机][CS229 _ 2]
 *  [机器学习技法 1 – Linear Support Vector Machine][1 _ Linear Support Vector Machine]
 *  [机器学习技法 2 – Dual Support Vector Machine][2 _ Dual Support Vector Machine]
 *  [机器学习技法 3 – Kernel Support Vector Machine][3 _ Kernel Support Vector Machine]
 *  [机器学习技法 4 – Soft-Margin Support Vector Machine][4 _ Soft-Margin Support Vector Machine]
 *  [机器学习技法 6 – Support Vector Regression][6 _ Support Vector Regression]
 *  [Scikit-learn 秘籍 第四章 使用 scikit-learn 对数据分类][Scikit-learn _ _ _ scikit-learn]
 *  [PythonProgramming.net 系列教程 第二部分 分类][PythonProgramming.net _ _ 1]
 *  [写给人类的机器学习 2.2 监督学习 II][2.2 _ II]
 *  [Python 数据分析与挖掘实战 第9章　基于水色图像的水质评价][Python _ _9]
 *  [数据科学和人工智能技术笔记 十五、支持向量机][Link 8]
 *  [Sklearn 学习指南 第二章：监督学习][Sklearn _]

### K 近邻 ###

*  [AILearning 第2章\_K近邻算法][AILearning _2_K]
 *  [Scikit-learn 秘籍 第三章 使用距离向量构建模型][Scikit-learn _ _ 1]
 *  [PythonProgramming.net 系列教程 第二部分 分类][PythonProgramming.net _ _ 1]
 *  [写给人类的机器学习 2.3 监督学习 III][2.3 _ III]
 *  [SciPyCon 2018 sklearn 教程 五、监督学习第一部分：分类][SciPyCon 2018 sklearn _ 1]
 *  [SciPyCon 2018 sklearn 教程 六、监督学习第二部分：回归分析][SciPyCon 2018 sklearn _ 2]
 *  [数据科学和人工智能技术笔记 十四、K 最近邻][_K]

### KMeans ###

*  [AILearning 第10章\_KMeans聚类][AILearning _10_KMeans]
 *  [CS229 中文笔记 十三、聚类][CS229 _ 3]
 *  [Scikit-learn 秘籍 第三章 使用距离向量构建模型][Scikit-learn _ _ 1]
 *  [PythonProgramming.net 系列教程 第三部分 聚类][PythonProgramming.net _ _ 2]
 *  [写给人类的机器学习 三、无监督学习][Link 9]
 *  [Python 数据分析与挖掘实战 第5章　挖掘建模][Python _ _5]
 *  [Python 数据分析与挖掘实战 第7章　航空公司客户价值分析][Python _ _7]
 *  [Python 数据分析与挖掘实战 第8章　中医证型关联规则挖掘][Python _ _8]
 *  [与 TensorFlow 的初次接触 3. TensorFlow 中的聚类][TensorFlow _ 3. TensorFlow]
 *  [SciPyCon 2018 sklearn 教程 八、无监督学习第二部分：聚类][SciPyCon 2018 sklearn _ 5]
 *  [TensorFlow 学习指南 三、学习][TensorFlow _]
 *  [数据科学和人工智能技术笔记 十七、聚类][Link 10]
 *  [Sklearn 学习指南 第三章：无监督学习][Sklearn _ 1]

### 均值移动 ###

*  [PythonProgramming.net 系列教程 第三部分 聚类][PythonProgramming.net _ _ 2]
 *  [数据科学和人工智能技术笔记 十七、聚类][Link 10]
 *  [Sklearn 学习指南 第三章：无监督学习][Sklearn _ 1]

### 层次聚类 ###

*  [写给人类的机器学习 三、无监督学习][Link 9]
 *  [Python 数据分析与挖掘实战 第14章　基于基站定位数据的商圈分析][Python _ _14]
 *  [SciPyCon 2018 sklearn 教程 二十、无监督学习：层次和基于密度的聚类算法][SciPyCon 2018 sklearn _ 6]
 *  [数据科学和人工智能技术笔记 十七、聚类][Link 10]
 *  [Sklearn 学习指南 第三章：无监督学习][Sklearn _ 1]

### DBSCAN ###

*  [SciPyCon 2018 sklearn 教程 二十、无监督学习：层次和基于密度的聚类算法][SciPyCon 2018 sklearn _ 6]
 *  [数据科学和人工智能技术笔记 十七、聚类][Link 10]

### 高斯混合 ###

*  [Scikit-learn 秘籍 第三章 使用距离向量构建模型][Scikit-learn _ _ 1]
 *  [Sklearn 学习指南 第三章：无监督学习][Sklearn _ 1]

### Boosting/Bagging/Blending ###

*  [机器学习技法 7 – Blending and Bagging][7 _ Blending and Bagging]

### AdaBoost ###

*  [AILearning 第7章\_集成方法][AILearning _7]
 *  [机器学习技法 8 – Adaptive Boosting][8 _ Adaptive Boosting]

### PCA ###

*  [AILearning 第13章\_PCA降维][AILearning _13_PCA]
 *  [AILearning 第14章\_SVD简化数据][AILearning _14_SVD]
 *  [CS229 中文笔记 十四、降维][CS229 _ 3]
 *  [写给人类的机器学习 三、无监督学习][Link 9]
 *  [SciPyCon 2018 sklearn 教程 七、无监督学习第一部分：变换][SciPyCon 2018 sklearn _ 7]
 *  [Sklearn 学习指南 第三章：无监督学习][Sklearn _ 1]

### LDA ###

*  [Scikit-learn 秘籍 第四章 使用 scikit-learn 对数据分类][Scikit-learn _ _ _ scikit-learn]

### 流形学习 ###

*  [SciPyCon 2018 sklearn 教程 二十一、无监督学习：非线性降维][SciPyCon 2018 sklearn _ 8]

### 异常检测 ###

*  [CS229 中文笔记 十五、异常检测][CS229 _ 4]
 *  [SciPyCon 2018 sklearn 教程 二十二、无监督学习：异常检测][SciPyCon 2018 sklearn _ 9]

### Apriori/FP-growth ###

*  [AILearning 第11章\_Apriori算法][AILearning _11_Apriori]
 *  [AILearning 第12章\_FP-growth算法][AILearning _12_FP-growth]
 *  [Python 数据分析与挖掘实战 第5章　挖掘建模][Python _ _5]
 *  [Python 数据分析与挖掘实战 第8章　中医证型关联规则挖掘][Python _ _8]

## 深度学习 ##

### 基础知识 ###

*  [DLAI 深度学习笔记 第一门课 第一周：深度学习引言][DLAI _ _ 1]
 *  [与 TensorFlow 的初次接触 1. TensorFlow 基础知识][TensorFlow _ 1. TensorFlow]
 *  [TensorFlow 学习指南 一、基础][TensorFlow _ 1]

### MLP ###

*  [CS229 中文笔记 八、神经网络：表述][CS229 _ 5]
 *  [CS229 中文笔记 九、神经网络的学习][CS229 _ 6]
 *  [DLAI 深度学习笔记 第一门课 第三周：浅层神经网络][DLAI _ _ 2]
 *  [DLAI 深度学习笔记 第一门课 第四周：深层神经网络][DLAI _ _ 3]
 *  [机器学习技法 12 – Neural Network][12 _ Neural Network]
 *  [机器学习技法 13 – Deep Learning][13 _ Deep Learning]
 *  [机器学习技法 14 – Radial Basis Function Network][14 _ Radial Basis Function Network]
 *  [PythonProgramming.net 系列教程 第四部分 神经网络][PythonProgramming.net _ _ 3]
 *  [写给人类的机器学习 四、神经网络和深度学习][Link 11]
 *  [Python 数据分析与挖掘实战 第5章　挖掘建模][Python _ _5]
 *  [Python 数据分析与挖掘实战 第6章　电力窃漏电用户自动识别][Python _ _6]
 *  [Python 数据分析与挖掘实战 第10章　家用电器用户行为分析与事件识别][Python _ _10]
 *  [Python 数据分析与挖掘实战 第13章　财政收入影响因素分析及预测模型][Python _ _13]
 *  [与 TensorFlow 的初次接触 4. TensorFlow 中的单层神经网络][TensorFlow _ 4. TensorFlow]
 *  [与 TensorFlow 的初次接触 5. TensorFlow 中的多层神经网络][TensorFlow _ 5. TensorFlow]
 *  [TensorFlow Rager 教程 一、如何使用 TensorFlow Eager 构建简单的神经网络][TensorFlow Rager _ _ TensorFlow Eager]
 *  [数据科学和人工智能技术笔记 十八、Keras][_Keras]

### CNN ###

*  [DLAI 深度学习笔记 第四门课 第一周 卷积神经网络][DLAI _ _ _]
 *  [DLAI 深度学习笔记 第四门课 第二周 深度卷积网络：实例探究][DLAI _ _ _ 1]
 *  [TensorFlow Rager 教程 七、使用 TensorFlow Eager 构建用于情感识别的卷积神经网络（CNN）][TensorFlow Rager _ _ TensorFlow Eager _CNN]

### RNN ###

*  [DLAI 深度学习笔记 第五门课 第一周 循环序列模型][DLAI _ _ _ 2]
 *  [DLAI 深度学习笔记 第五门课 第三周 序列模型和注意力机制][DLAI _ _ _ 3]
 *  [TensorFlow Rager 教程 八、用于 TensorFlow Eager 序列分类的动态循坏神经网络][TensorFlow Rager _ _ TensorFlow Eager 1]
 *  [TensorFlow Rager 教程 九、用于 TensorFlow Eager 时间序列回归的递归神经网络][TensorFlow Rager _ _ TensorFlow Eager 2]

## 时间序列 ##

*  [第5章　挖掘建模][Python _ _5]
 *  [Python 数据分析与挖掘实战 第11章　应用系统负载分析与磁盘容量预测][Python _ _11]
 *  [TensorFlow Rager 教程 九、用于 TensorFlow Eager 时间序列回归的递归神经网络][TensorFlow Rager _ _ TensorFlow Eager 2]

## 机器视觉 ##

*  [CS229 中文笔记 十八、应用实例：图片文字识别][CS229 _ 7]
 *  [DLAI 深度学习笔记 第四门课 第三周 目标检测][DLAI _ _ _ 4]
 *  [DLAI 深度学习笔记 第四门课 第四周 特殊应用：人脸识别和神经风格转换][DLAI _ _ _ 5]
 *  [PythonProgramming.net 系列教程 图像和视频分析][PythonProgramming.net _]
 *  [PythonProgramming.net 系列教程 TensorFlow 目标检测][PythonProgramming.net _ TensorFlow]
 *  [数据科学和人工智能技术笔记 四、图像预处理][Link 12]

## 图嵌入/图的表示学习 ##

*  [图嵌入综述：问题，技术与应用 第一、二章][Link 13]
 *  [图嵌入综述：问题，技术与应用 第三章][Link 14]
 *  [图嵌入综述：问题，技术与应用 4.1 ~ 4.2][4.1 _ 4.2]
 *  [图嵌入综述：问题，技术与应用 4.3 ~ 4.7][4.3 _ 4.7]
 *  [图嵌入综述：问题，技术与应用 第五、六、七章][Link 15]

## 自然语言处理 ##

*  [DLAI 深度学习笔记 第五门课 第二周 自然语言处理与词嵌入][DLAI _ _ _ 6]
 *  [PythonProgramming.net 系列教程 自然语言处理教程][PythonProgramming.net _ 1]
 *  [PythonProgramming.net 系列教程 TensorFlow 聊天机器人][PythonProgramming.net _ TensorFlow 1]
 *  [Python 数据分析与挖掘实战 第15章　电商产品评论数据情感分析][Python _ _15]
 *  [TensorFlow Rager 教程 七、使用 TensorFlow Eager 构建用于情感识别的卷积神经网络（CNN）][TensorFlow Rager _ _ TensorFlow Eager _CNN]
 *  [TensorFlow Rager 教程 八、用于 TensorFlow Eager 序列分类的动态循坏神经网络][TensorFlow Rager _ _ TensorFlow Eager 1]
 *  [SciPyCon 2018 sklearn 教程 十一、文本特征提取][SciPyCon 2018 sklearn _ 10]
 *  [SciPyCon 2018 sklearn 教程 十二、案例学习：用于 SMS 垃圾检测的文本分类][SciPyCon 2018 sklearn _ _ SMS]
 *  [SciPyCon 2018 sklearn 教程 二十三、核外学习 - 用于语义分析的大规模文本分类][SciPyCon 2018 sklearn _ _ -]
 *  [数据科学和人工智能技术笔记 五、文本预处理][Link 16]

## 强化学习 ##

*  [写给人类的机器学习 五、强化学习][Link 17]

## 推荐系统 ##

*  [AILearning 第16章\_推荐系统][AILearning _16]
 *  [CS229 中文笔记 十六、推荐系统][CS229 _ 4]
 *  [机器学习技法 15 – Matrix Factorization][15 _ Matrix Factorization]
 *  [Python 数据分析与挖掘实战 第12章　电子商务网站用户行为分析及服务推荐][Python _ _12]
 *  [基于深度学习的推荐系统：综述和新视角 第一、二章][Link 18]
 *  [基于深度学习的推荐系统：综述和新视角 3.1 ~ 3.3][3.1 _ 3.3]
 *  [基于深度学习的推荐系统：综述和新视角 3.4 ~ 3.11][3.4 _ 3.11]

## 预处理/特征工程 ##

*  [Scikit-learn 秘籍 第一章 模型预处理][Scikit-learn _ _ 2]
 *  [Python 数据分析与挖掘实战 第3章　数据探索][Python _ _3]
 *  [Python 数据分析与挖掘实战 第4章　数据预处理][Python _ _4]
 *  [TensorFlow Rager 教程 四、文本序列到 TFRecords][TensorFlow Rager _ _ TFRecords]
 *  [TensorFlow Rager 教程 五、如何将原始图片数据转换为 TFRecords][TensorFlow Rager _ _ TFRecords 1]
 *  [TensorFlow Rager 教程 六、如何使用 TensorFlow Eager 从 TFRecords 批量读取数据][TensorFlow Rager _ _ TensorFlow Eager _ TFRecords]
 *  [SciPyCon 2018 sklearn 教程 三、数据表示和可视化][SciPyCon 2018 sklearn _ 11]
 *  [SciPyCon 2018 sklearn 教程 七、无监督学习第一部分：变换][SciPyCon 2018 sklearn _ 7]
 *  [SciPyCon 2018 sklearn 教程 十、案例学习：泰坦尼克幸存者][SciPyCon 2018 sklearn _ 12]
 *  [SciPyCon 2018 sklearn 教程 十一、文本特征提取][SciPyCon 2018 sklearn _ 10]
 *  [SciPyCon 2018 sklearn 教程 十九、自动特征选择][SciPyCon 2018 sklearn _ 13]
 *  [数据科学和人工智能技术笔记 二、数据准备][Link 19]
 *  [数据科学和人工智能技术笔记 三、数据预处理][Link 20]
 *  [数据科学和人工智能技术笔记 四、图像预处理][Link 12]
 *  [数据科学和人工智能技术笔记 五、文本预处理][Link 16]
 *  [数据科学和人工智能技术笔记 六、日期时间预处理][Link 21]
 *  [数据科学和人工智能技术笔记 七、特征工程][Link 22]
 *  [数据科学和人工智能技术笔记 八、特征选择][Link 23]
 *  [数据科学和人工智能技术笔记 十九、数据整理（上）][Link 24]
 *  [数据科学和人工智能技术笔记 十九、数据整理（下）][Link 25]
 *  [数据科学和人工智能技术笔记 二十、数据可视化][Link 26]
 *  [Sklearn 学习指南 第四章：高级功能][Sklearn _ 2]

## 模型评估/模型调优 ##

*  [CS229 中文笔记 七、正则化][CS229 _ 1]
 *  [CS229 中文笔记 十、应用机器学习的建议][CS229 _ 8]
 *  [CS229 中文笔记 十一、机器学习系统的设计][CS229 _ 8]
 *  [DLAI 深度学习笔记 第二门课 第一周：深度学习的实用层面][DLAI _ _ 4]
 *  [DLAI 深度学习笔记 第二门课 第三周超参数调试，batch正则化和程序框架][DLAI _ _ _batch]
 *  [DLAI 深度学习笔记 第三门课 第一周：机器学习策略（1）][DLAI _ _ _1]
 *  [DLAI 深度学习笔记 第三门课 第二周：机器学习策略（2）][DLAI _ _ _2]
 *  [机器学习基石 5 – Training versus Testing][5 _ Training versus Testing]
 *  [机器学习基石 13 – Hazard of Overfitting][13 _ Hazard of Overfitting]
 *  [机器学习基石 14 – Regularization][14 _ Regularization]
 *  [机器学习基石 15 – Validation][15 _ Validation]
 *  [Scikit-learn 秘籍 第二章 处理线性模型][Scikit-learn _ _]
 *  [Scikit-learn 秘籍 第五章 模型后处理][Scikit-learn _ _ 3]
 *  [TensorFlow Rager 教程 二、在 Eager 模式中使用指标][TensorFlow Rager _ _ Eager]
 *  [SciPyCon 2018 sklearn 教程 四、训练和测试数据][SciPyCon 2018 sklearn _ 14]
 *  [SciPyCon 2018 sklearn 教程 十三、交叉验证和得分方法][SciPyCon 2018 sklearn _ 15]
 *  [SciPyCon 2018 sklearn 教程 十四、参数选择、验证和测试][SciPyCon 2018 sklearn _ 16]
 *  [SciPyCon 2018 sklearn 教程 十六、模型评估、得分指标和处理不平衡类别][SciPyCon 2018 sklearn _ 17]
 *  [TensorFlow 学习指南 二、线性模型][TensorFlow _ 2]
 *  [数据科学和人工智能技术笔记 九、模型验证][Link 27]
 *  [数据科学和人工智能技术笔记 十、模型选择][Link 28]
 *  [Sklearn 学习指南 第四章：高级功能][Sklearn _ 2]

## 最优化 ##

### 梯度下降 ###

*  [CS229 中文笔记 十七、大规模机器学习][CS229 _ 7]
 *  [DLAI 深度学习笔记 第一门课 第二周：优化算法][DLAI _ _ 5]

## 其它 ##

*  [机器学习技法 16（完结） – Finale][16_ _ Finale]
 *  [CS229 中文笔记 十九、总结][CS229 _ 7]
 *  [写给人类的机器学习 六、最好的机器学习资源][Link 29]
 *  [与 TensorFlow 的初次接触 6. 并行][TensorFlow _ 6.]
 *  [TensorFlow Rager 教程 三、如何保存和恢复训练模型][TensorFlow Rager _]
 *  [TensorFlow 学习指南 四、分布式][TensorFlow _ 3]
 *  [数据科学和人工智能技术笔记 二十一、统计学][Link 30]

## 关于我们 ##

> 我们是一个大型开源社区，旗下 QQ 群共 9000 余人，订阅用户至少一万人。Github Star 数量超过 20k 个，在所有 Github 组织中[排名前 200][200]。网站日 uip 超过 4k，[Alexa 排名的峰值为 20k][Alexa _ 20k]。我们的核心成员拥有[ CSDN 博客专家][CSDN]和[简书程序员优秀作者][Link 31]认证。我们与 [Datawhale][]、[AI 有道][AI]、[黄海广博士][Link 32]等国内知名开源组织和大 V 合作，组织公益性的翻译活动、学习活动和比赛组队活动。
> 
> 与商业组织不同，我们并不会追逐热点，或者唯利是图。作为公益组织，我们将完成项目放在首要位置，并有足够时间把项目打磨到极致。我们希望做出广大 AI 爱好者真正需要的东西，打造真正有价值的长尾作品。

*  【导航】[ibooker.org.cn][]
 *  【归档】[home.apachecn.org][]
 *  【社区】[bbs.apachecn.org][]
 *  【Github】[@ApacheCN][ApacheCN]
 *  自媒体平台
    
     *  [微博：@ApacheCN][ApacheCN 1]
     *  [知乎专栏：AILearning][AILearning 1]
     *  [公众号：ApacheCN][ApacheCN 2]
     *  [CSDN][CSDN 1] | [博客园][Link 33] | [简书][Link 34] | [bilibili][]
 *  **We are ApacheCN Open Source Organization, not ASF! We are fans of AI, and have no relationship with ASF!**
 *  合作 or 侵权，请联系 [apachecn@163.com][apachecn_163.com] | 请抄送一份到 [wizard.z@foxmail.com][wizard.z_foxmail.com]

![ApacheCN 2][]

## 赞助我们 ##

![donate.jpg][]

[CodingNet.png]: /images/20220130/5801aaa21b3a4a259657d9788fe721a3.png
[CodingNet.png 1]: https://coding.net/?utm_source=ApacheCN&utm_medium=banner&utm_campaign=march2019
[Link 1]: https://github.com/wizardforcel
[AILearning _1]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/1.%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E5%9F%BA%E7%A1%80.md
[CS229 _]: http://ai-start.com/ml2014/html/week1.html
[1 _ The Learning Problem]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/2.md
[2 _ Learning to Answer Yes_No]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/3.md
[3 _ Types of Learning]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/4.md
[4 _ Feasibility of Learning]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/5.md
[6 _ Theory of Generalization]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/7.md
[7 _ The VC Dimension]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/8.md
[8 _ Noise and Error]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/9.md
[16 _ Three Learning Principles]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/17.md
[Link 2]: https://github.com/apachecn/ml-for-humans-zh/blob/master/1.md
[SciPyCon 2018 sklearn _ _Python]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/1.md
[SciPyCon 2018 sklearn _ _Python 1]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/2.md
[SciPyCon 2018 sklearn _ _sklearn]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/9.md
[SciPyCon 2018 sklearn _]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/15.md
[Link 3]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/1.md
[Sklearn _ _ -]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/learning-sklearn/ch01.md
[AILearning _5]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/5.Logistic%E5%9B%9E%E5%BD%92.md
[AILearning _8]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/8.%E5%9B%9E%E5%BD%92.md
[CS229 _ 1]: http://ai-start.com/ml2014/html/week2.html
[DLAI _ _]: http://ai-start.com/dl2017/html/lesson1-week2.html
[9 _ Linear Regression]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/10.md
[10 _ Logistic Regression]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/11.md
[11 _ Linear Models for Classification]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/12.md
[12 _ Nonlinear Transformation]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/13.md
[5 _ Kernel Logistic Regression]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/23.md
[Scikit-learn _ _]: https://github.com/apachecn/sklearn-cookbook-zh/blob/master/2.md
[Scikit-learn _ _ _ scikit-learn]: https://github.com/apachecn/sklearn-cookbook-zh/blob/master/4.md
[PythonProgramming.net _ _]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/python-programming-net/python-programming-net-ml/1.md
[2.1]: https://github.com/apachecn/ml-for-humans-zh/blob/master/2.1.md
[2.2 _ II]: https://github.com/apachecn/ml-for-humans-zh/blob/master/2.2.md
[Python _ _5]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/5.md
[Python _ _13]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/13.md
[TensorFlow _ 2. TensorFlow]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/first_contact_with_tensorFlow/2.md
[SciPyCon 2018 sklearn _ 1]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/5.md
[SciPyCon 2018 sklearn _ 2]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/6.md
[SciPyCon 2018 sklearn _ 3]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/17.md
[Link 4]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/11.md
[Link 5]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/12.md
[Sklearn _]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/learning-sklearn/ch02.md
[AILearning _3]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/3.%E5%86%B3%E7%AD%96%E6%A0%91.md
[AILearning _9]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/9.%E6%A0%91%E5%9B%9E%E5%BD%92.md
[9 _ Decision Tree]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/27.md
[10 _ Random Forest]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/28.md
[2.3 _ III]: https://github.com/apachecn/ml-for-humans-zh/blob/master/2.3.md
[Python _ _6]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/6.md
[SciPyCon 2018 sklearn _ 4]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/18.md
[Link 6]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/13.md
[11 _ Gradient Boosted Decision Tree]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/29.md
[AILearning _4]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/4.%E6%9C%B4%E7%B4%A0%E8%B4%9D%E5%8F%B6%E6%96%AF.md
[Link 7]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/16.md
[AILearning _6]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/6.%E6%94%AF%E6%8C%81%E5%90%91%E9%87%8F%E6%9C%BA.md
[AILearning]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/6.1.%E6%94%AF%E6%8C%81%E5%90%91%E9%87%8F%E6%9C%BA%E7%9A%84%E5%87%A0%E4%B8%AA%E9%80%9A%E4%BF%97%E7%90%86%E8%A7%A3.md
[CS229 _ 2]: http://ai-start.com/ml2014/html/week7.html
[1 _ Linear Support Vector Machine]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/19.md
[2 _ Dual Support Vector Machine]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/20.md
[3 _ Kernel Support Vector Machine]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/21.md
[4 _ Soft-Margin Support Vector Machine]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/22.md
[6 _ Support Vector Regression]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/24.md
[PythonProgramming.net _ _ 1]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/python-programming-net/python-programming-net-ml/2.md
[Python _ _9]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/9.md
[Link 8]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/15.md
[AILearning _2_K]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/2.k-%E8%BF%91%E9%82%BB%E7%AE%97%E6%B3%95.md
[Scikit-learn _ _ 1]: https://github.com/apachecn/sklearn-cookbook-zh/blob/master/3.md
[_K]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/14.md
[AILearning _10_KMeans]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/10.k-means%E8%81%9A%E7%B1%BB.md
[CS229 _ 3]: http://ai-start.com/ml2014/html/week8.html
[PythonProgramming.net _ _ 2]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/python-programming-net/python-programming-net-ml/3.md
[Link 9]: https://github.com/apachecn/ml-for-humans-zh/blob/master/3.md
[Python _ _7]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/7.md
[Python _ _8]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/8.md
[TensorFlow _ 3. TensorFlow]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/first_contact_with_tensorFlow/3.md
[SciPyCon 2018 sklearn _ 5]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/8.md
[TensorFlow _]: https://github.com/apachecn/learning-tf-zh/blob/master/3.md
[Link 10]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/17.md
[Sklearn _ 1]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/learning-sklearn/ch03.md
[Python _ _14]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/14.md
[SciPyCon 2018 sklearn _ 6]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/20.md
[7 _ Blending and Bagging]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/25.md
[AILearning _7]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/7.%E9%9B%86%E6%88%90%E6%96%B9%E6%B3%95-%E9%9A%8F%E6%9C%BA%E6%A3%AE%E6%9E%97%E5%92%8CAdaBoost.md
[8 _ Adaptive Boosting]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/26.md
[AILearning _13_PCA]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/13.%E5%88%A9%E7%94%A8PCA%E6%9D%A5%E7%AE%80%E5%8C%96%E6%95%B0%E6%8D%AE.md
[AILearning _14_SVD]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/14.%E5%88%A9%E7%94%A8SVD%E7%AE%80%E5%8C%96%E6%95%B0%E6%8D%AE.md
[SciPyCon 2018 sklearn _ 7]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/7.md
[SciPyCon 2018 sklearn _ 8]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/21.md
[CS229 _ 4]: http://ai-start.com/ml2014/html/week9.html
[SciPyCon 2018 sklearn _ 9]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/22.md
[AILearning _11_Apriori]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/11.%E4%BD%BF%E7%94%A8Apriori%E7%AE%97%E6%B3%95%E8%BF%9B%E8%A1%8C%E5%85%B3%E8%81%94%E5%88%86%E6%9E%90.md
[AILearning _12_FP-growth]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/12.%E4%BD%BF%E7%94%A8FP-growth%E7%AE%97%E6%B3%95%E6%9D%A5%E9%AB%98%E6%95%88%E5%8F%91%E7%8E%B0%E9%A2%91%E7%B9%81%E9%A1%B9%E9%9B%86.md
[DLAI _ _ 1]: http://ai-start.com/dl2017/html/lesson1-week1.html
[TensorFlow _ 1. TensorFlow]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/first_contact_with_tensorFlow/1.md
[TensorFlow _ 1]: https://github.com/apachecn/learning-tf-zh/blob/master/1.md
[CS229 _ 5]: http://ai-start.com/ml2014/html/week4.html
[CS229 _ 6]: http://ai-start.com/ml2014/html/week5.html
[DLAI _ _ 2]: http://ai-start.com/dl2017/html/lesson1-week3.html
[DLAI _ _ 3]: http://ai-start.com/dl2017/html/lesson1-week4.html
[12 _ Neural Network]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/30.md
[13 _ Deep Learning]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/31.md
[14 _ Radial Basis Function Network]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/32.md
[PythonProgramming.net _ _ 3]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/python-programming-net/python-programming-net-ml/4.md
[Link 11]: https://github.com/apachecn/ml-for-humans-zh/blob/master/4.md
[Python _ _10]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/10.md
[TensorFlow _ 4. TensorFlow]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/first_contact_with_tensorFlow/4.md
[TensorFlow _ 5. TensorFlow]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/first_contact_with_tensorFlow/5.md
[TensorFlow Rager _ _ TensorFlow Eager]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/1.md
[_Keras]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/18.md
[DLAI _ _ _]: http://ai-start.com/dl2017/html/lesson4-week1.html
[DLAI _ _ _ 1]: http://ai-start.com/dl2017/html/lesson4-week2.html
[TensorFlow Rager _ _ TensorFlow Eager _CNN]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/7.md
[DLAI _ _ _ 2]: http://ai-start.com/dl2017/html/lesson5-week1.html
[DLAI _ _ _ 3]: http://ai-start.com/dl2017/html/lesson5-week3.html
[TensorFlow Rager _ _ TensorFlow Eager 1]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/8.md
[TensorFlow Rager _ _ TensorFlow Eager 2]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/9.md
[Python _ _11]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/11.md
[CS229 _ 7]: http://ai-start.com/ml2014/html/week10.html
[DLAI _ _ _ 4]: http://ai-start.com/dl2017/html/lesson4-week3.html
[DLAI _ _ _ 5]: http://ai-start.com/dl2017/html/lesson4-week4.html
[PythonProgramming.net _]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/python-programming-net/python-programming-net-opencv.md
[PythonProgramming.net _ TensorFlow]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/python-programming-net/python-programming-net-tf-object-detection.md
[Link 12]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/4.md
[Link 13]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/ge-survey-arxiv-1709-07604-zh/1.md
[Link 14]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/ge-survey-arxiv-1709-07604-zh/2.md
[4.1 _ 4.2]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/ge-survey-arxiv-1709-07604-zh/3.md
[4.3 _ 4.7]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/ge-survey-arxiv-1709-07604-zh/4.md
[Link 15]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/ge-survey-arxiv-1709-07604-zh/5.md
[DLAI _ _ _ 6]: http://ai-start.com/dl2017/html/lesson5-week2.html
[PythonProgramming.net _ 1]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/python-programming-net/python-programming-net-nltk.md
[PythonProgramming.net _ TensorFlow 1]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/python-programming-net/python-programming-net-tf-chatbot.md
[Python _ _15]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/15.md
[SciPyCon 2018 sklearn _ 10]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/11.md
[SciPyCon 2018 sklearn _ _ SMS]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/12.md
[SciPyCon 2018 sklearn _ _ -]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/23.md
[Link 16]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/5.md
[Link 17]: https://github.com/apachecn/ml-for-humans-zh/blob/master/5.md
[AILearning _16]: https://github.com/apachecn/AiLearning/blob/master/docs/ml/16.%E6%8E%A8%E8%8D%90%E7%B3%BB%E7%BB%9F.md
[15 _ Matrix Factorization]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/33.md
[Python _ _12]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/12.md
[Link 18]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/rs-survey-arxiv-1707-07435-zh/1.md
[3.1 _ 3.3]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/rs-survey-arxiv-1707-07435-zh/2.md
[3.4 _ 3.11]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/rs-survey-arxiv-1707-07435-zh/3.md
[Scikit-learn _ _ 2]: https://github.com/apachecn/sklearn-cookbook-zh/blob/master/1.md
[Python _ _3]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/3.md
[Python _ _4]: https://github.com/apachecn/python_data_analysis_and_mining_action/blob/gitbook/4.md
[TensorFlow Rager _ _ TFRecords]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/4.md
[TensorFlow Rager _ _ TFRecords 1]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/5.md
[TensorFlow Rager _ _ TensorFlow Eager _ TFRecords]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/6.md
[SciPyCon 2018 sklearn _ 11]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/3.md
[SciPyCon 2018 sklearn _ 12]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/10.md
[SciPyCon 2018 sklearn _ 13]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/19.md
[Link 19]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/2.md
[Link 20]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/3.md
[Link 21]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/6.md
[Link 22]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/7.md
[Link 23]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/8.md
[Link 24]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/19.1.md
[Link 25]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/19.2.md
[Link 26]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/20.md
[Sklearn _ 2]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/learning-sklearn/ch04.md
[CS229 _ 8]: http://ai-start.com/ml2014/html/week6.html
[DLAI _ _ 4]: http://ai-start.com/dl2017/html/lesson2-week1.html
[DLAI _ _ _batch]: http://ai-start.com/dl2017/html/lesson2-week3.html
[DLAI _ _ _1]: http://ai-start.com/dl2017/html/lesson3-week1.html
[DLAI _ _ _2]: http://ai-start.com/dl2017/html/lesson3-week2.html
[5 _ Training versus Testing]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/6.md
[13 _ Hazard of Overfitting]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/14.md
[14 _ Regularization]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/15.md
[15 _ Validation]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/16.md
[Scikit-learn _ _ 3]: https://github.com/apachecn/sklearn-cookbook-zh/blob/master/5.md
[TensorFlow Rager _ _ Eager]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/2.md
[SciPyCon 2018 sklearn _ 14]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/4.md
[SciPyCon 2018 sklearn _ 15]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/13.md
[SciPyCon 2018 sklearn _ 16]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/14.md
[SciPyCon 2018 sklearn _ 17]: https://github.com/apachecn/scipycon-2018-sklearn-tut-zh/blob/master/16.md
[TensorFlow _ 2]: https://github.com/apachecn/learning-tf-zh/blob/master/2.md
[Link 27]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/9.md
[Link 28]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/10.md
[DLAI _ _ 5]: http://ai-start.com/dl2017/html/lesson2-week2.html
[16_ _ Finale]: https://github.com/apachecn/ntu-hsuantienlin-ml/blob/master/34.md
[Link 29]: https://github.com/apachecn/ml-for-humans-zh/blob/master/6.md
[TensorFlow _ 6.]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/first_contact_with_tensorFlow/6.md
[TensorFlow Rager _]: https://github.com/apachecn/misc-docs-zh/blob/master/docs/tf-eager-tut/3.md
[TensorFlow _ 3]: https://github.com/apachecn/learning-tf-zh/blob/master/4.md
[Link 30]: https://github.com/apachecn/ds-ai-tech-notes/blob/master/21.md
[200]: https://gitstar-ranking.com/apachecn
[Alexa _ 20k]: https://www.alexa.com/siteinfo/apachecn.org
[CSDN]: https://blog.csdn.net/wizardforcel
[Link 31]: https://www.jianshu.com/u/b508a6aa98eb
[Datawhale]: http://home.apachecn.org/img/about/datawhale_qr.jpg
[AI]: http://home.apachecn.org/img/about/redstone_qr.jpg
[Link 32]: http://home.apachecn.org/img/about/huanghaiguang_qr.jpg
[ibooker.org.cn]: http://www.ibooker.org.cn/
[home.apachecn.org]: http://home.apachecn.org
[bbs.apachecn.org]: http://bbs.apachecn.org/
[ApacheCN]: https://github.com/apachecn
[ApacheCN 1]: https://weibo.com/u/6326715527
[AILearning 1]: https://zhuanlan.zhihu.com/apachecn-mlia
[ApacheCN 2]: /images/20220130/f9ac3429a8954e65bdb5602228f3f137.png
[CSDN 1]: https://blog.csdn.net/wizardforcel/article/category/8437073
[Link 33]: https://www.cnblogs.com/wizardforcel/category/1352397.html
[Link 34]: https://www.jianshu.com/c/4ee721d0c474
[bilibili]: http://space.bilibili.com/97678687
[apachecn_163.com]: mailto:apachecn@163.com
[wizard.z_foxmail.com]: mailto:wizard.z@foxmail.com
[donate.jpg]: /images/20220130/dd17a8e8fcd04a32b716aee977f52af2.png