Overview of the most interesting materials on data analysis and machine learning №15 (September 22 - 28, 2014)

I present to you the next issue of the review of the most interesting materials on the topic of data analysis and machine learning.

General

• IBM Watson gets closer to business and regular users.
• New language-independent NLP library
• How big data changes the face of companies
• Analysis of existing approaches to face recognition
• Presentations from the New PostgreSQL 9.4 and Something More Meeting
  Not long ago, a meeting was held in the office of the Yandex company dedicated to the PostgreSQL DBMS, and already now you can watch presentations from the reports that were presented at this meeting.
• 10 Big Data Tools
  10 Big Data tools from the DZone blog, which can be useful for data analysts.
• 20 open data sources
  The SmartData Collective portal has published an interesting list of 20 data sources that can be useful to data analysts.
• How Google uses Deep Learning to combat spam
  An interesting article about how Google uses Deep Learning to combat spam.
• Introduction to In-Memory Computing
  Another interesting guide to analyzing data from the popular portal insideBIGDATA. In this case, this is an introduction to In-Memory Computing.
• Introduction to Predictive Analytics (Part 4)
  The fourth part of a series of articles from the insideBIGDATA portal on Predictive Analytics. The fourth part will discuss the use of the R programming language in Predictive Analytics.
• List of interesting resources
  A list of interesting sites and resources on Data Science, visualization, machine learning and big data from the popular DataScienceCentral portal.
• Introduction to Big Data in the financial sector
  The insideBIGDATA portal announces a new series of articles on data analysis. In this series, we will discuss the use of Big Data in the financial sector.
• Choosing a GPU for machine learning
  An interesting article about the choice and use of GPU for computing when using machine learning Deep Learning.
• Deep Learning Bibliography
  The most popular articles from the bibliography on the subject of Deep Learning.
• 43 Data Science Leaders
  The list of 43 leaders in the field of Data Science according to the DataScienceCentral portal.
• 5 most attractive data analysis professions
  Article from the popular portal Smart Data Collective, which describes the 5 possible areas of activity in the field of data analysis (Data Scientist, Technical Architect, Machine Learning Expert, Hadoop Engineer, Data Marketing Executive).
• KDD - two themes
  A short article from the Microdoft Technet Machine Learning blog about the KDD conference and the Azure ML cloud product.
• 50 blogs worth reading
  A good list of 50 blogs on statistics, machine learning and data analysis, which will be interesting to read, presented by the popular portal DataScienceCentral.
• How Baidu Applies Deep Learning
  An interesting story about how Baidu uses Deep Learning machine learning algorithms in its work.
• How search works
  A small infographics from Google about how search works.

Machine learning competitions

• Experience from participating in the Display Advertising Challenge
  An interesting article about the experience gained from participating in the machine competition "Display Advertising Challenge" on Kaggle, which ended recently.
• Using R, H2O and Domino on Kaggle
  An interesting article about using the R programming language in conjunction with Domino and H2O in a machine learning competition called “Africa Soil Property Prediction Challenge” on Kaggle.

Online courses and training materials

• Online Course "Statistical Learning"
  In January 2014, Stanford University conducted an online course based on the new book An Introduction to Statistical Learning with Applications in R (ISLR). In this post will be presented videos and presentations from this course.
• Online Course "The Caltech-JPL Summer School on Big Data Analytics"
  A rather unusual online course started in the middle of September at Coursera. In essence, this is a collection of video lectures and materials from the summer school of machine learning from the California Institute of Technology.
• Online course "Learning From Data"
  Recently, edX launched a new session of this very popular machine learning course from the California Institute of Technology and Professor Yaser Abu-Mostafa as the main instructor.

')

Literature

• Review of the book “Frequent Pattern Mining”
  Review of the book "Frequent Pattern Mining", published in 2014, from the portal KDnuggets.
• The book "R for Cloud Computing"
  The announcement of a very interesting book on cloud computing using the R programming language, which will soon be available.

Theory and algorithms of machine learning, code examples

• What is Feature Engineering
  Excellent article from the author of the blog MachineLearningMastery about the process of Feature Engineering in machine learning.
• Dynamic Learning and Sub-Linear Debugging
  Another article from the blog of Microsoft Technet Machine Learning. This time, the article will cover the topic of dynamic learning (Online Learning) and Sub-Linear Debugging.
• Introduction to the support vector method
  A very simple and brief introduction to the Support Vector Machines method.
• Data Processing with Python
  This article from the Analytics blog Vidhya talks about data processing using the Python programming language and the Pandas library.
• Comparison and selection of training models with R Caret
  Another article from the author of the blog MachineLearningMastery, devoted to the possibilities of the Caret machine learning library for the R programming language. In this case, we will discuss the comparison of training models and the choice of the most effective one.
• How to publish ggplot2 graphics
  Useful article on how to publish graphs made using the ggplot2 library for the R programming language, in the form of a web page.
• Work with Twitter through REST API and R
  A good article describing the ability to work with Twitter data through the REST API using the RTwitterAPI library for the R programming language.
• Parameter selection with R Caret
  The author of the blog MachineLearningMastery talks about the functionality of feature selection (Feature Selection) in the popular machine learning library Caret for the R programming language.
• Factors are not first class objects in R
  A rather large article describing the subtleties and possible problems in working with factors in the R programming language.
• Dependency management in R
  An interesting article about dependency management between libraries in the R programming language, as well as about visualizing this data about dependencies between libraries.

Video

• The use of big data in the financial and banking sectors
  The insideBIGDATA portal published a rather interesting video in an article titled Big Data in Banking and Financial Services, which is devoted to the possibilities of using big data in the financial and banking sector.

Data engineering

• Spark 1.1: MLlib performance improvements
  A small article on how performance improvements in the new version of Apache Spark have impacted the work of the MLlib machine learning library.
• 5 tips on working with NoSQL-storages
  5 useful tips from the High Scalability portal on scaling NoSQL-storages.
• Introduction to YARN
  A good introduction to YARN for Hadoop 2 from insideBIGDATA portal.
• 120 companies that are interested in Hadoop developers
  This post contains a list of 120 companies that are interested in Hadoop-developers with a small description of how Hadoop is used in the company.
• Performance Cloudera Impala 1.4
  Cloudera Impala 1.4 performance test results compared to other products from the Cloudera blog.

Reviews

• Top KDnuggets articles (September 21 - 27)
  The list of the best articles of the popular KDnuggets portal from September 21 to September 27.
• Digest of the best resources from DataScienceCentral
  A good list of fresh interesting articles and resources from DataScienceCentral.
• Weekly Digest from DataScienceCentral
  Regular weekly digest of articles on data analysis from the DataScienceCentral portal.
• Data Mining News
  A small list of interesting resources on Data Mining on September 24.
• Top Articles KDnuggets (September 14 - 20)
  The list of the best articles of the portal of the popular KDnuggets from September 14 to 20.
• Freakonometrics # 167 Most Interesting Materials
  Collection of the most interesting materials from the popular portal Freakonometrics
• The most interesting materials from Freakonometrics №166
  Collection of the most interesting materials from the popular portal Freakonometrics
• The most interesting materials on High Scalability
  Review of the most interesting materials on HighScalability from the popular High Scalability portal.

Previous release: Review of the most interesting materials on data analysis and machine learning №14 (September 15 - 21, 2014)