Nearly 200 Machine Learning & deep learning materials sharing (including various documents, videos, source code, etc.) (1)

Nearly 200 Machine Learning & deep learning materials sharing (including various documents, videos, source code, etc.) (1)

Editor's note: This article collects hundreds of articles about machine learning and deep learning, including various documents, videos, and source code. In addition, the original text will be updated from time to time. I hope that my friends who see the article can learn more.

Brief History of Machine Learning

Introduction: this is an article about the history of machine Learning. It covers a wide range of topics, from perception machines, neural networks, decision trees, SVM, Adaboost to random forests and Deep Learning.

Deep Learning in Neural Networks: An Overview

Introduction: this is the latest version of neural network and deep learning, written by Swiss AI laboratory Jurgen mongodhuber. The features of this overview are time-ordered, starting from January 1, to August 1, we have been talking about the progress since 2000 and in recent years. It covers various tricks in deep learning and provides comprehensive references.

A Gentle Introduction to Scikit-Learn: A Python Machine Learning Library

Introduction: This is a python Machine Learning Library. If you are a python engineer and want to learn machine learning in depth, this article may help you.

How to Layout and Manage Your Machine Learning Project

Introduction: This article describes how to design and manage your own machine learning projects. It provides management templates, data management, and practical methods.

Machine Learning is Fun!

Introduction: If you still don't know what machine learning is, or it is just a boring learning experience. We recommend that you read it. This article has been translated into Chinese and can be moved to http://blog.jobbole.com/67616/ if interested

R language reference card

Introduction: The R language is the main language for machine learning. Many friends want to learn the R language, but they always forget the meaning of some functions and keywords. This article may help you

Choosing a Machine Learning Classifier

Introduction: How can I choose a machine learning algorithm? This article intuitively compares the advantages and disadvantages of methods such as Naive Bayes, Logistic Regression, SVM, and decision tree, we also discuss the sample size, the trade-off between Feature and Model. There is also a version that has been translated: http://www.52ml.net/15063.html

An Introduction to Deep Learning: From Perceptrons to Deep Networks

Introduction: Deep Learning Overview: From the perception machine to the deep network, the author's selection of examples and theoretical introductions are all in place. Http://www.cnblogs.com/xiaowanyer/p/3701944.html.

The LION Way: Machine Learning plus Intelligent Optimization

Introduction: <machine learning and optimization> This is a machine learning brochure that covers all aspects of machine learning in just over 300 pages. images and texts are vivid and easy to understand, and there are no worries about formulas. it is suitable for beginners to lay the foundation, and also for veterans to learn new things. you may need more than MLAPP/PRML! Specific content recommended read: http://intelligent-optimization.org/LIONbook/

Deep Learning and Statistical Learning Theory

Description: The author is from Baidu, but he has already applied to resign in January. However, this article is very good. If you do not know the relationship between deep learning and SVM/statistical learning theory, what is the relationship between them? You should read this article immediately.

Mathematics in Computer Science

Introduction: This book is Mathematics in Computer Science jointly produced by Google and MIT: Mathematics for Computer Science, Eric Lehman et al 2013. Divided into five parts: 1) proof, induction. 2) structure, number theory, and graph. 3) count, sum, and generate a function. 4) probability, random walk. 5) recursion. And so on.

Foundations of Data Science

Introduction: Computer Science Theory in the information age. Currently, there are paper books and iTunes books in China.

Data Science with R

Introduction: this is a new version of "data science getting started" by Xuecheng University. It is practical and easy to understand. It is suitable for students who want to learn the R language.

Twenty Questions for Donald Knuth

Introduction: this is not a document or book. This is a record of a question to the Turing Award winner Donald Knuth: Recently, Charles Leiserson, Al Aho, Jon Bentley, and other experts raised 20 questions to Knuth, including the TAOCP and P/NP questions, turing Machine, logic, and why don't you use emails.

Automatic Construction and Natural-Language Description of Nonparametric Regression Models

Introduction: What if no statistics are collected? I don't know how to select an appropriate statistical model. What should I do? In this article, you read Joshua B. Tenenbaum from MIT and Zoubin Ghahramani from Cambridge, and wrote an article about automatic statistician. You can automatically select a regression model category and write reports automatically...

ICLR 2014 proceedings

Introduction: if you are interested in the latest development of deep learning and representation learning, please take a look.

Introduction to Information Retrieval

Introduction: this is a book related to Information Retrieval. Introduction to Information Retrieval, co-authored by Stanford Manning and Google Vice President Raghavan, has always been one of the most popular Information Retrieval textbooks in North America. Recently, the author added slides and assignments for the course. IR resources: http://www-nlp.stanford.edu/IR-book/information-retrieval.html

Machine learning in 10 pictures

Description: Deniz Yuret uses 10 beautiful pictures to explain the important concepts of machine learning: 1. bias/Variance Tradeoff 2. overfitting 3. bayesian/Occam's razor 4. feature combination 5. irrelevant feature 6. basis function 7. discriminative/Generative 8. loss function 9. least squares 10. sparsity. very clear

Yahoo Research Institute dataset Summary

Description: DataSet Summary of Yahoo Research Institute: includes language data, graph and social data, scoring and classification data, calculation of advertising data, image data, competition data, and system data.

An Introduction to Statistical Learning with Applications in R

Introduction: this is a new book by famous Stanford statistics professors Trevor Hastie and Robert Tibshirani and has started classes in January 2014: https://class.stanford.edu/courses/HumanitiesScience/StatLearning/Winter2014/about

Best Machine Learning Resources for Getting Started

Introduction: the best learning materials for getting started with machine learning is a high-quality learning resource designed for beginners of machine learning to help beginners get started quickly. The introduction of this article has been translated into the Chinese version. If you are not familiar with it, I suggest you take a look at the introduction of Chinese.

My deep learning reading list

Description: This document is mainly found in Bengio's PAMI review article. This article includes several summary articles, nearly 100 papers, and Presentation of various mountain heads. All can be found on google.

Cross-Language Information Retrieval

Introduction: This is a book that focuses on cross-language information retrieval. Many theories

Explore the secrets inside the receng, Part 1: Initial Exploration of receng

Introduction: This article consists of three series by IBM engineers. It mainly introduces recommendation engine algorithms and helps readers efficiently implement these algorithms. Explore internal secrets of the receng, Part 1: Deep recommendation engine related algorithms-collaborative filtering, exploring secrets within the receng, Part 2: Deep recommendation engine related algorithms-Clustering

Advice for students of machine learning

Introduction: David Mimno, Assistant Professor in the Information Science Department of Cornell University, wrote "some suggestions for beginners of machine learning", which is very practical and emphasizes the combination of practice and theory, at last, he cited the famous saying "Young man, in mathematics you don't understand things. you just get used to them."

Distributed Parallel processing of data

Introduction: this is A copy of Distributed Parallel Processing Data called deployments in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercises. The author is James L. McClelland of Stanford. This section focuses on the Distributed implementation of various God-level network algorithms. For more information about Distributed Deep Learning, see

What is "Machine Learning"?

Introduction: what is "Machine Learning ?] John Platt is an outstanding scientist at Microsoft Research Institute. He has been working in the machine learning field for 17 years. In recent years, machine learning has become a hot topic. Platt and his colleagues decided to open a blog to introduce the progress of machine learning research to the public. What is machine learning and where is it applied? Let's take a look at this blog post on Platt.

ICML 2014 paper at 2014 International Machine Learning Conference

Introduction: The 2014 International Machine Learning Conference ICML was held at the National Convention Center on June 21-26. This conference was jointly sponsored by Microsoft's Asia Research Institute and Tsinghua University. It was the first time that the Conference was held in China in the machine learning field that has been well-known for more than 30 years, it has successfully attracted more than 1200 scholars from home and abroad. There are a lot of dry goods and it is worth further study

Machine Learning for Industry: A Case Study

Introduction: This article mainly uses Learning to Rank as an example to describe the specific application of machine Learning in the business world. RankNet is not sensitive to NDCG. After NDCG is added, it becomes LambdaRank, lambdaMART is achieved by changing the idea from neural networks to applying the Boosted Tree model. Chirs Burges, the master of Microsoft machine Learning, the first winner of Yahoo 2010 Learning to Rank Challenge, RankNet, LambdaRank, and LambdaMART in terms of sorting models, which are particularly prominent in LambdaMART: from RankNet to LambdaRank to LambdaMART: An Overview In addition, Burges has many well-known representatives, such as A Tutorial on Support Vector Machines for Pattern Recognition.

Some Notes on Applied Mathematics for Machine Learning

100 Best GitHub: Deep Learning

Introduction: 100 Best GitHub: Deep Learning

UFLDL-Professor Andrew Ng at Stanford University "Deep Learning" tutorial

Introduction: This tutorial describes the main points of view of unsupervised feature learning and deep learning. Through learning, you will also implement multiple function learning/deep learning algorithms to see that they work for you and learn how to apply/adapt to these ideas to new problems. This tutorial assumes that the basic knowledge of machine learning is especially familiar with supervised learning, logistic regression, and gradient descent ideas.) If you are not familiar with these ideas, we recommend that you go to the machine learning course here, complete chapter II, III, IV to logistic regression first ). In addition, the source Code of this Tutorial has already had the python version UFLDL Tutorial Code on github.

*Deep Learning for Natural Language Processing and Related Applications

Description: This document is from Microsoft Research Institute and contains many essence. If you need to fully understand it, you need a certain amount of machine learning basics. However, in some places, it may make people shine.

Understanding Convolutions

Introduction: this is an article about image convolution, which is detailed.

Machine Learning Summer School

Introduction: I invite daniel to give a lecture every day, covering machine learning, big data analysis, parallel computing, and human brain research. Https://www.youtube.com/user/smolix needs FQ)

Awesome Machine Learning

Introduction: a summary of a super complete open source machine learning library. If you think this is a bunker, this list will surprise you even more: Awesome Awesomeness ], some enthusiastic domestic friends have introduced Chinese translation, and machine learning data mining is a free ebook.

Stanford natural language processing course video

Introduction: all the videos of the "natural language processing" course by ACL President and Professor Chris Manning from the computer department of Stanford University can be viewed on the Stanford Open Class website. If Chrome doesn't work, you can watch it with IE) you can also download assignments and quizzes.

Deep Learning and Shallow Learning

Introduction: This article compares Deep Learning and Shallow Learning with the blog of Chiyuan Zhang, a graduate of Zhejiang University and a graduate of MIT.

Recommending music on Spotify with deep learning

Introduction: Uses convolutional Neural Networks for music recommendation.

Neural Networks and Deep Learning

Introduction: Neural Network free online book, has written three chapters, there is a corresponding open source code: the gospel of https://github.com/mnielsen/neural-networks-and-deep-learning lovers.

Java Machine Learning

Introduction: Java machine Learning platforms and open-source machine Learning libraries are organized based on big data, NLP, computer vision, and Deep Learning. It looks comprehensive, and Java fans are worth collecting.

Machine Learning Theory: An Introductory Primer

Introduction: the most basic introduction to machine learning, suitable for beginners

Classification summary of common Machine Learning Algorithms

Introduction: There are many machine learning algorithms. Many people are confused that many algorithms are a class of algorithms, and some algorithms are extended from other algorithms. Here, we will introduce you from two aspects: the first is the learning method, and the second is the similarity of algorithms.

Typical machine learning papers/survey collection

Introduction: You already know what the question is. There are many classic machine learning papers worth reading carefully and repeatedly.

Machine Learning Video Library

Introduction: the video is produced by Caltech of Caltech. English is required.

Classic books on Machine Learning

Introduction: summarizes the classic books of machine learning, including books on mathematical basics and algorithm theory. This can be used as a reference document for beginners.

16 Free eBooks On Machine Learning

Introduction: 16 machine learning e-books can be downloaded and read at any time on the pad and mobile phone. Not much. I suggest you read one and then download one.

A Large set of Machine Learning Resources for Beginners to Mavens

Introduction: The title is very big, from novice to expert. But after reading all the above materials. It must be an expert.

Summary of the best learning materials for Machine Learning

Introduction: There are a lot of books for getting started, and I have already helped you find them.

Sibyl

Introduction: Sibyl is a supervised machine learning system used to solve prediction problems, such as YouTube video recommendations.

Deep Learning

Introduction: Yoshua Bengio, Ian Goodfellow, by Aaron Courville

Neural Network & Text Mining

Introduction: summary of some paper in NLP and Text Mining of (Deep) Neural Networks

Summary of foreground Target Detection 1)

Introduction: foreground Target Detection for computer vision 1)

Pedestrian detection

Introduction: Pedestrian detection for Computer Vision beginners

Deep Learning-important resources for learning and understanding

Introduction: Important resources for learning and understanding. Is awesome

Machine Learning Theory: An Introductory Primer

Introduction: This is an introduction for beginners of machine learning. Worth reading

Neural Networks and Deep Learning

Introduction: online Neural Networks and Deep Learning ebook

Python web crawler & Text Processing & Scientific Computing & Machine Learning & Data Mining

Introduction: 17 machine learning tools for python