Get into the habit of writing together! This is the 18th day of my participation in the "Nuggets Daily New Plan · April Update Challenge", click to view the details of the event .
Recently, because of work needs, I have to learn machine learning. Because I am also a novice in this technology, so I will record the materials of machine learning, and I suggest collecting or commenting on any useful introductory machine learning tutorials.
official information
For the authoritative official, of course, Google 's tutorial. The entire tutorial system is very comprehensive. The machine learning crash course is very distinctive with a series of courses, including video lectures, real-world case studies and hands-on practice exercises. Friends with good English can get started directly.
Second, is Microsoft's tutorial . Microsoft's Azure Cloud Advocate offers a 12-week, 26-hour course on machine learning. In this course, you'll learn what is sometimes called classic machine learning, primarily using Scikit-learn as a library.
third party information
MorvanZhou
machine learning introductory tutorial, including video tutorials, text tutorials, etc. in great detail, this buddy wrote tutorials in his spare time, and recorded videos, explained in Chinese, you can go to station B to enjoy.
mlcourse.ai is
a set of machine learning courses. The course is comprehensive and detailed, with demos and advanced Kaggle competition examples, which are very suitable for beginners to learn in depth step by step.
waifu2x
makes pictures and photos high-definition based on machine learning. This project uses a convolutional neural network to perform 1-2x lossless enlargement operations on images, and supports noise reduction to ensure image quality.
Machine Learning in Action by ailearning
ApacheCN. Supporting video: Strong coding ability, it is recommended to watch "Machine Learning Practice - Teaching Edition". Weak coding ability, it is recommended to watch "Machine Learning in Practice - Discussion Edition".
"Statistical Learning Methods" written by Mr. Li Hang from lihang-code
comprehensively and systematically introduces the main methods of statistical learning, especially supervised learning methods, including perceptron, k-nearest neighbor method, naive Bayes method, decision tree, logistic Regression and Support Vector Machines, Boosting Methods, EM Algorithms, Hidden Markov Models and Conditional Random Fields, etc. With the exception of Chapter 1 Introduction and the last Chapter Summary, each chapter introduces a method. The narration starts with specific problems or examples, proceeds from simple to deep, clarifies ideas, and gives necessary mathematical derivation, so that readers can grasp the essence of statistical learning methods and learn to use them.
There are many materials related to machine learning, so I will not list them one by one.
development related
Some commonly used python libraries, including but not limited to:
- numpy matrix operations
- scipy numerical operations
- matplotlib plotting library
- pandas data cleaning
- sklearn algorithm library
It is recommended to use the Anaconda tool to easily obtain and manage packages, and use it to manage the release version of the environment in a unified manner. Excitingly, Anaconda includes over 180 scientific packages including conda, Python and their dependencies.
What about development tools? There are many options, I generally use PyCharm, because I am a heavy user of Jetbrains development tools, of course you can also use VS Code for development.