“Machine learning Beginners” public account 2019 selected original articles collection, suitable for beginners to start AI. This article suggests using wechat to collect, with fragments of time to learn. (Huang Haiguang)

## Introduction:

The biggest problem for AI beginners is: too much information!! Can’t finish it!! Don’t know how to choose!! People’s energy is limited!!

I sorted out the original or selected articles of the official account since 2019, and sorted out the learning route and material collection, which is suitable for undergraduate, master’s and doctoral students who are new to machine learning.

After learning these articles, you will have a basic introduction.

After entry, encounter a problem to be able to search the Internet to solve, also know what should learn next.

This paper suggests using wechat to collect and use fragmented time to learn.

## I am writing :AI foundation

AI Basics: An easy introduction to math

AI Basics: Python development environment setup and tips

AI Basics: Easy to get started with Python

AI Basics: Numpy easy to get started

AI Foundation: Pandas

AI Basics: Scipy(Scientific Computing Library) easy introduction

AI Basics: An easy introduction to Data Visualization (Matplotlib and Seaborn)

AI Fundamentals: Use of machine learning library SciKit-learn

AI Basics: An easy introduction to machine learning

AI Fundamentals: Loss functions for machine learning

AI Fundamentals: Feature Engineering – Category Features

AI Fundamentals: Feature Engineering – Digital feature processing

AI fundamentals: Feature Engineering – Text feature processing

AI basics: Word embedding basics and Word2Vec

AI basics: Illustrated Transformer

AI basics: Understand BERT

AI fundamentals: A must-see paper for introduction to artificial intelligence

AI Fundamentals: Into deep learning

AI Fundamentals: Deep Learning

AI Fundamentals: An overview of data enhancement methods

Continue to update in 2020!

## Second, learning route

• Starting:Suitable for beginners to enter the artificial intelligence route and information download

This article provides an introductory route for beginners. It includes basic mathematics, Introduction to Python, machine learning, Deep learning, introduction to feature engineering, etc. And put the code in the Github repository:

Github.com/fengdu78/Da…

## Three, basic knowledge

• Take you to avoid detours!! Machine learning math basics to help you (available online)

The above article is basics of Math and is a consolidated version of the following five articles, which can be read online or separately as needed.

• Starting:The mathematical foundation of Ng’s CS229 (Probability theory), someone made it into an online translation!
• Starting:The mathematical foundations of Ng’s CS229 (linear Algebra), someone made it into an online translation!
• Read online!!Machine learning mathematics essence:Higher mathematics
• Read online!!Machine learning mathematics essence:Linear algebra
• Read online!! Machine learning mathematics essence: Probability theory and mathematical statistics

## Machine learning

• Machine Learning Online Manual:Learn machine learning like memorizing TOEFL words

This article has made the essence of machine learning into a manual, which can be learned by opening wechat. It is suitable for friends who have little time to learn machine learning, and they can study on their mobile phones when commuting. It is suggested to collect this article and learn slowly

The original works are as follows: \

• Machine Learning Course Notes and Resources (Github star 12000+, baidu cloud image provided)
• Python code implementation of Statistical Learning Methods (Github 7200+)
• Recommendation:Machine Learning in Action:Scikit-learn and TensorFlow based on Chinese translation and code download

And then an online version:

• Take you to avoid detours:Learn ng machine learning in five articles
• Classic reproductions:Statistical Learning Methods code implementation (online reading!)

#### Machine learning correlation

• Where can I find machine learning exercise data?Two lines of code!
• – Data analysis with Python 2 (Code and Chinese notes)
• Feature Engineering for Machine Learning translation and code implementation
• Starting:The two latest machine learning papers published by Prof. Yita Hsu’s team

## Deep learning

#### Ng deep Learning course Notes and resources

• Ng deep learning notes, videos and other resources (Github standard star 8500+, providing Baidu cloud image)
• ## 330000 words!Deep Learning Notes online edition released!

#### TensorFlow entry:

• Take you to avoid detours:Highly recommended TensorFlow Quick Start materials and translations (downloadable)

#### Keras entry:

• Take you off the wrong track: Highly recommended Keras Quick Start materials and translations (downloadable)

#### Pytorch entry:

• Take you to avoid detours:Highly recommended Pytorch Quick Start materials and translations (downloadable)

### Other information

• Starting:Introduction to Deep Learning – “Python deep Learning” source code Annotated in Chinese and ebook
• Highly recommended sample resources for TensorFlow, Pytorch, and Keras (a must for deep learning beginners)
• Ubuntu 18.04 Deep Learning Configuration (CUDA9.0+CUDDN7.4+TensorFolw1.8)

## 6. Python

• Personal advice and information for getting started with Python
• Installation of Python (Anaconda+Jupyter Notebook +Pycharm)
• What if Python code is ugly?Recommend a few artifacts to save you
• Numpy Exercises 100 – Improve your data analysis skills
• Pandas Exercises – Improve your data analysis skills
• Fundamentals of Python Drawing Tools – Basic use of matplotlib learning
• Data visualization tools -Seaborn easy to get started

## Seven, NLP

• Some introductory NLP references
• Recommendation:Code implementation of common NLP models (based on TensorFlow and PyTorch)
• Word2vec