Introduction: Learning is a complex intelligent activity. The learning process is closely related to the reasoning process. According to the amount of reasoning used in learning, the strategies adopted by machine learning can be roughly divided into four types-machine learning, learning through teaching , Learning by analogy and learning through examples. The more reasoning used in learning, the more capable the system is.
First, a brief introduction to machine learning
The core of machine learning artificial intelligence is the fundamental way to make computers intelligent. Its application pervades all fields of artificial intelligence. It mainly uses induction and synthesis rather than deduction.
- supervised learning
|
|
- Unsupervised learning
|
|
——Data processing and model tuning
|
|
Research work in the field of machine learning mainly revolves around the following three aspects:
(1) Task-Oriented Research: Study and analyze learning systems that improve performance on a set of predetermined tasks.
(2) Cognitive models: study the human learning process and conduct computer simulations.
(3) Theoretical analysis: theoretically explore various possible learning methods and algorithms independent of the application domain
Machine learning is another important research field of artificial intelligence application after expert system, and it is also one of the core research topics of artificial intelligence and neural computing. Existing computer systems and artificial intelligence systems have no learning ability, at best only a very limited learning ability, so they cannot meet the new requirements of technology and production. The discussion of machine learning and the progress of machine learning research will surely promote the further development of artificial intelligence and the entire science and technology.
Machine learning has been used in a wide range of applications, such as: data mining, computer vision, natural language processing, biological special detection recognition, search engines, medical diagnosis, DNA sequence sequencing, speech and handwriting recognition, strategic games and robot applications.
Recommend organized machine learning introductory learning resources
1. Tools
Scikit-Learn Official Documentation
As a very comprehensive library for machine learning, Scikit-Learn is a rare practical programming manual.
2. Public class
Ng Enda Coursera "Machine Learning"
This is definitely the first choice course for getting started with machine learning, not one of them! Getting Started with Machine Learning Made Easy!
Wu Enda (1976-, English name: Andrew Ng), a Chinese American, is an associate professor in the Department of Computer Science and Electrical Engineering at Stanford University, and the director of the Artificial Intelligence Laboratory. Wu Enda is one of the most authoritative scholars in the field of artificial intelligence and machine learning in the world.
On May 16, 2014, Wu Enda joined Baidu as the chief scientist of Baidu, responsible for the leadership of Baidu Research Institute, especially the Baidu Brain project.
Wu Enda Stanford cs229 video
The machine learning course CS229 taught by Wu Enda at Stanford is slightly more difficult.
Lin Xuantian "The Cornerstone of Machine Learning"
Lin Xuantian: Professor Lin Xuantian received a bachelor's degree from the Department of Information Engineering, National Taiwan University in 2001, and a master's and doctoral degree from the California Institute of Technology in 2005 and 2008. He returned to the Department of Information Engineering of National Taiwan University as an assistant professor in 2008, was promoted to an associate professor in 2012, and was promoted to a professor in August 2017. He won the KDDCup world championship for four consecutive years (six times).
The "Foundation of Machine Learning" course taught by Professor Lin Xuantian of National Taiwan University is comprehensive and covers many aspects of the field of machine learning. It is very suitable as an introductory and advanced material for machine learning. Moreover, Teacher Lin's teaching style is also very humorous, always allowing readers to master knowledge in a relaxed and pleasant atmosphere. This course is slightly more difficult than Ng's "Machine Learning", focusing on machine learning theoretical knowledge.
Lin Xuantian "Machine Learning Techniques"
The "Machine Learning Techniques" course is an advanced course of "Machine Learning Foundations". It mainly introduces some classic algorithms in the field of machine learning, including support vector machines, decision trees, random forests, neural networks, etc. The difficulty is slightly higher than "Foundation of Machine Learning", which is very practical.
Need to scan the code to add the above video and information
3. Books
Zhou Zhihua "Machine Learning"
Zhou Zhihua, male, graduated from the Department of Computer Science and Technology of Nanjing University (Bachelor, Master, Ph.D.), and stayed in the school to teach in 2001. Now a professor at Nanjing University, a doctoral supervisor; winner of the National Outstanding Youth Fund; director of the Department of Computer Science and Technology of Nanjing University, dean of the School of Artificial Intelligence, executive deputy director of the State Key Laboratory of New Computer Software Technology, machine learning and data mining research Director of the institute (LAMDA), member of the academic committee of the school and department.
This "Machine Learning" is known as the "Watermelon Book". This book is very classic. It tells the core mathematical theory and algorithm of machine learning. It is suitable for school textbooks or self-study for intermediate readers. It is a little more difficult to learn this book when you get started.
Li Hang "Statistical Learning Methods"
This book comprehensively and systematically introduces the main methods of statistical learning. It is suitable for college students and graduate students majoring in text data mining, information retrieval and natural language processing in colleges and universities. It can also be used as a reference for R&D personnel engaged in computer application related majors.
Published by Tsinghua University Press, author: Li Hang
A Practical Guide to Machine Learning with Scikit-Learn and TensorFlow
After the previous study, this "Scikit-Learn and TensorFlow Machine Learning Practical Guide" is very suitable for improving your machine learning practical programming ability.
This book is divided into two parts. The first part introduces basic machine learning algorithms, and each chapter is equipped with Scikit-Learn practical projects; the second part introduces neural networks and deep learning, and each chapter is equipped with TensorFlow practical projects. If it's just machine learning, you can read the content of the first part first.
Four, actual combat
Kaggel competition——Competition is the most effective way to improve one's actual machine learning ability. Kaggle competition is the first choice.
The editor has compiled information about artificial intelligence, including resource libraries such as image processing opencv\natural language processing, machine learning mathematics foundation, must-read e-books, and collections of papers. College students who want to learn artificial intelligence or switch to high-paying industries are also very interested. Practical, free of charge without any routine,
Add my skirt [ 966367816 ] to download, or scan the code + vx to get the internal resources, artificial intelligence question bank, Dachang interview question study outline self-study course outline and 500G artificial intelligence data spree for free~
