Machine Learning Table of Elements Decoded

The Machine Learning periodic table from MLN.io, a machine learning newsletter, lists machine learning packages for languages like Python and Java and tasks like NLP and Computer Vision.
http://www.mln.io/resources/periodic-table/

機器學習--超參數相關設定範圍

http://blog.kaggle.com/2016/07/21/approaching-almost-any-machine-learning-problem-abhishek-thakur/



http://machinelearningmastery.com/configure-gradient-boosting-algorithm/

機器學習、深度學習與自然語言處理領域推薦的書籍列表

https://segmentfault.com/a/1190000008598352

機器學習

• 2007 - Pattern Recognition And Machine Learning【Book】 : The book is suitable for courses on machine learning, statistics, computer science, signal processing, computer vision, data mining, and bioinformatics.
• 2012 - Machine Learning A Probabilistic Perspective 【Book】 : This textbook offers a comprehensive and self-contained introduction to the field of machine learning, a unified, probabilistic approach. The coverage combines breadth and depth, offering necessary background material on such topics as probability , optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning.
• 2012 -李航:統計方法學：李航老師的這本書偏優化和推倒，推倒相應算法的時候可以參考這本書。
• 2014 - DataScience From Scratch【Book】 : In this book, you'll learn how many of the most fundamental data science tools and algorithms work by implementing them from scratch.
• 2015 - Python Data Science Handbook【Book】 :Jupyter Notebooks for the Python Data Science Handbook
• 2015 - Data Mining, The Textbook【Book】 : This textbook explores the different aspects of data mining from the fundamentals to the complex data types and their applications, capturing the wide diversity of problem domains for data mining issues.
• 2016 -周志華機器學習【Book】：周志華老師的這本書非常適合作為機器學習入門的書籍，書中的例子十分形象且簡單易懂。
• University of Illinois at Urbana-Champaign:Text Mining and Analytics【Course】
• 台大機器學習技法【Course】
• 斯坦福機器學習課程【Course】
• CS224d: Deep Learning for Natural Language Processing【Course】
• Unsupervised Feature Learning and Deep Learning【Course】 :來自斯坦福的無監督特徵學習與深度學習系列教程
• 史上最全的机器学习资料（下）涵蓋24種編程語言的機器學習的框架、庫以及其他相關資料https://my.oschina.net/freegodly/blog/740027 

深度學習

• 2015-The Deep Learning Textbook【Book】 :中文譯本這裡，The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. The online version of the book is now complete and will remain available online for free.
• Stanford Deep Learning Tutorial【Book】 : This tutorial will teach you the main ideas of Unsupervised Feature Learning and Deep Learning. By working through it, you will also get to implement several feature learning/deep learning algorithms, get to see them work for yourself , and learn how to apply/adapt these ideas to new problems.
• Neural Networks and Deep Learning【Book】 : Neural Networks and Deep Learning is a free online book. The book will teach you about: (1) Neural networks, a beautiful biologically-inspired programming paradigm which enables a computer to learn from observational data. (2) Deep learning, a powerful set of techniques for learning in neural networks
• Practical Deep Learning For Coders 【Course】 :七週的免費深度學習課程，學習如何構建那些優秀的模型。
• Oxford Deep NLP 2017 course【Course】 : This is an advanced course on natural language processing. Automatically processing natural language inputs and producing language outputs is a key component of Artificial General Intelligence.

自然語言處理

• 2016 - CS224d: Deep Learning for Natural Language Processing【Course】
• 2017 - Oxford Deep NLP 2017 course【Course】
• [2015 - Text Data Management and Analysis【Book】](): A Practical Introduction to Information Retrieval and Text Mining
• DL4NLP-Deep Learning for NLP resources【Resource】

Agile Knowledge Engineering and Semantic Web (AKSW)

一個有關semantic web和knowledge engineering的研究群，http://aksw.org/About.html

hosted by the Chair of Business Information Systems (BIS) of the Institute of Computer Science (IfI) / University of Leipzig as well as the Institute for Applied Informatics (InfAI).

Goals

• Development of methods, tools and applications for adaptive Knowledge Engineering in the context of the Semantic Web
• Research of underlying Semantic Web technologies and development of fundamental Semantic Web tools and applications
• Maturation of strategies for fruitfully combining the Social Web paradigms with semantic knowledge representation techniques

AKSW is committed to the free software, open source, open access and open knowledge movements.

Groups


The following subgroups belong to AKSW

• Adaptive Information and Knowledge Engineering
• Agile collaborative requirements engineering
• Creation and evolution of knowledge bases from legacy databases
• Software product-line engineering
• Vocabulary alignment
• Emergent Semantics
• Agile Knowledge Engineering
• Distributed / Federated Social Networks
• Linked Data
• Semantic Software Engineering
• Semantic Web Infrastructure
• Knowledge Integration and Linked Data Technologies
• Data Engineering
• Data Integration
• Data-driven Artificial Intelligence
• DBpedia
• Knowledge Engineering
• Language Technology
• Machine Learning and Ontology Engineering
• Creating knowledge bases from weakly structured data
• Quality assurance and enhancement in ontologies
• Semi-automatic instance matching
• Supervised Machine Learning in OWL/RDF knowledge bases
• Semantic Abstraction
• Knowledge Access, e.g., keyword-based search, question answering, and interfaces
• Knowledge Extraction, e.g., extraction of RDF and OWL from unstructured data
• Knowledge Integration, e.g., link discovery and linked data fusion
• Knowledge Storage, e.g., federated queries, triple stores
• Knowledge-Driven applications, e.g., industry 4.0, big data, benchmark

BigML Releases

https://bigml.com/releases

https://bigml.com/releases/fall-2016
Our Fall 2016 release brings Topic Models, the latest resource that helps you easily find thematically related terms in your text data. Discover BigML’s implementation of the underlying Latent Dirichlet Allocation (LDA) technique, one of the most popular probabilistic methods for topic modeling tasks. This resource is included in our FREE version and it is accessible from the BigML Dashboard as well as the API. Topic Models not only help you better understand and organize your collection of documents, but also can improve the performance of your models for information retrieval tasks, collaborative filtering, or when assessing document similarity.

WhizzML is a new domain-specific language for automating Machine Learning workflows, implementing high-level Machine Learning algorithms, and easily sharing them with others. WhizzML offers out-of-the-box scalability, abstracts away the complexity of underlying infrastructure, and helps analysts, developers, and scientists reduce the burden of repetitive and time-consuming analytics tasks.

https://bigml.com/releases/spring-2016

Model evaluation, model selection, and algorithm selection in machine learning

Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data
https://becominghuman.ai/cheat-sheets-for-ai-neural-networks-machine-learning-deep-learning-big-data-678c51b4b463


幫你選擇分類器的分類器：Auto-WEKA
Auto-WEKA是由Kotthoff等人開發來Weka分類器套件，Auto-WEKA的論文「Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA」已經在2016年底發表在Journal of Machine Learning Research。
http://blog.pulipuli.info/2017/04/auto-weka-automatic-model-selection-and.html

Part I - The basics
http://sebastianraschka.com/blog/2016/model-evaluation-selection-part1.html
Part II - Bootstrapping and uncertainties
http://sebastianraschka.com/blog/2016/model-evaluation-selection-part2.html
Part III -Cross-validation and hyperparameter tuning
http://sebastianraschka.com/blog/2016/model-evaluation-selection-part3.html


【轉貼】2016 前 20 大 Python 機器學習開源項目
https://buzzorange.com/techorange/2016/12/19/2016-top-20-python-machine-learning-open-source-projects/

Machine Learning Wars

Amazon vs Google vs BigML vs PredicSishttp://www.kdnuggets.com/2015/05/machine-learning-wars-amazon-google-bigml-predicsis.html

a tweet-size summary:
Amazon Machine Learning most accurate
BigML fastest
PredicSis best trade-off
Google (Prediction API) last

	Amazon	Google	PredicSis	BigML
Accuracy (AUC)	0.862	0.743	0.858	0.853
Time for training (s)	135	76	17	5
Time for predictions (s)	188	369	5	1

Machine Learning: A Complete and Detailed Overview

The 10 Algorithms Machine Learning 
http://www.kdnuggets.com/2016/08/10-algorithms-machine-learning-engineers.html

 Support Vector Machines

Naïve Bayes Classification

Decision Trees

Ordinary Least Squares Regression

Logistic Regression

Ensemble Methods

Clustering Algorithms

Principal Component Analysis

Independent Component Analysis

Singular Value Decomposition.