It is all about practical experience and best study materials for AI

• this repository is still updating...

Great thanks to brother yun contributing to this repository! Welcome more to contribute!

Basics model includes some essentially fundamental algorithms,such as bisection, Dijstra, common sort algorithms and so on.

• 二分法例子
• 迪杰斯特拉算法应用举例
• 牛顿法求f(x)解应用举例
• 闭包使用举例
• 普利姆算法求得最小生成树
• 堆排序求得TopK
• 快速排序求得TopK

Math model is exactly its seeming name, about math theories, especially about optimization, linear algebra, probabilty theory.

• KKT条件讲的最好的PPT
• 机器学习中的条件数怎么理解？

Python model is mainly for machine learning and deep learning ,such as decorator, generator, highOrder function, etc and that is to say, doesn't include everything knowledge about Python, currently including:

• 装饰器极简入门
• 生成器极简入门
• 高阶函数极简入门
• itertools之groupby
• 24式加速你的Python
• Python63个内置函数
• Type Checking
• 列表生成式
• Collections模块
• itertools模块

Numpy model is about numpy summaries in practice, currently including:

• Numpy特征工程常见的4个场景
• Numpy的切片索引使用举例

Pandas model is about pandas summaries in practice.

• Pandas实战总结1
• Pandas列索引获取方法
• Pandas列排序
• Pandas去重操作使用举例
• Pandas的loc索引
• Pandas的merge应用例子
• Pandas的多索引、轴、排序
• Pandas的Series使用例子
• Pandas的DataFrame使用例子
• to_csv乱码解决方法一
• Pandas处理缺失值实战

ML model is mainly about ml skill stack, including feature engineering, pca, common ml algorithms, etc. Importantly, each step of machine learning is provided the reference materials which are picked up elaborately, currently including:

• 入门机器学习，这是我见过的最直白讲解
• 单词拼写检查器
• 决策树做回归和分类及可视化
• 主成分分析之 PCA, SVD
• 手写 高斯混合GMM算法
• 手写 线性回归实战
• 手写 逻辑回归实战
• xgboost基础入门
• 梯度提升树(GBDT)完整教程 V1.1 发布.pdf
• 最常用的降维算法tsne

DL model,deep learning part contains theory about cv and nlp.

• lstm 网络模型原理剖析
• 前馈神经网络底层原理剖析
• 深度学习线性回归
• 手写字识别

Best study materials for deep learning:

• 深度学习极简入门笔记

Kaggle model is about in pracitce and contains sorts of practical experience.

Tensorflow model, tensorflow skeleton will be noted from introductory to practical application to projects.

​