Review of the most interesting materials on data analysis and machine learning №28 (December 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

• The five most important events in the world R at the end of 2014
• How can Deep Learning be used in various areas of life in the future?
• List of machine learning resources - an excellent list of machine learning resources divided into several thematic categories (Deep Learning, Online Learning, Ensemble Methods, Kernel Machines, GPU Learning, NLP, etc.)
• Spark Packages Announcement - Spark Packages Announcement: a collection of various open source libraries for Apache Spark.
• Interactive three-dimensional visualization of various data sets in the browser using data-projector
• Forecasts for 2015: what will happen to Big Data and Data Science? - Another forecast for the coming year from the popular portal KDnuggets.com.
• 7 Best Resources of 2014 by Big Data from SmartData Collective
• 8 Big Data Predictions for 2015 by SmartData Collective
• 4 Steps to Big Data Success in 2015
• 10 best articles of 2014 on Data Science from the blog Analytics Vidhya

Theory and algorithms of machine learning, code examples

• Hacker's guide to neural networks. Chapter 2: Machine Learning. Binary classification
• Hacker's guide to neural networks. Chapter 2: Machine Learning. Network learning based on support vector machine (SVM)
• Overview of graph compression algorithms
• InterSystems iKnow. We load data from VKontakte
• Linear algebra in machine learning - the author of the blog MachineLearningMastery talks about what aspects of linear algebra it is useful to know for a better understanding of machine learning algorithms.
• Collect and analyze baseball statistics with R
• Decision trees: building and cutting off branches
• Using the Principal Component Analysis method when working with images
• Recognition of handwritten numbers with R (part 1)
• Comparing Dataframe in Python, R and Julia
• An example of creating predictive models using the caret library is an example of using the popular caret library for the R programming language to create predictive models.
• Expanded version of the scikit-learn cheat sheet
• A set for machine learning is a large and useful set of various links to machine learning materials (including in Russian).
• Data visualization with GAE Python, D3.js and Google BigQuery (part 1)
• Data visualization with GAE Python, D3.js and Google BigQuery (part 2)
• Data Visualization with GAE Python, D3.js and Google BigQuery (Part 3)
• Spark Use Example (Part 3): Cleaning and Sorting Social Security Numbers
• Example code: applying a function to every line in data.frame

Machine learning competitions

• How to deal with problems on Kaggle - a set of simple tips from the author of the blog Analytics Vidhya, which will help you become a successful participant in machine learning competitions at Kaggle.
• Interview with Yann LeCun: convolutional networks and CIFAR-10 - an interesting interview with Yann LeCunn (Director of AI Research, Professor at New York University) on the use of convolutional networks and discussion of the recently completed Kaggle machine learning competition, which was devoted to image recognition issues.
• Analyzing Kaggle data with R is an interesting analysis of data from machine learning competitions at Kaggle using the R programming language.

Online courses, educational materials and literature

• The announcement of the online course “Statistics and R for the Life Sciences” - an interesting course called “Statistics and R for the Life Sciences” from Harvard University was announced at edX.
• Course materials "Convex Optimization" from Carnegie Mellon University
• A set of lectures from the course Principles of Distributed Computing (ETH Zürich)

Video

• The main pitfalls of machine learning projects are the interesting performance of Machine Learning Gremlins by Ben Hammer and comments from the author of the blog MachineLearningMastery.
• Machine learning with the help of statistical and casual methods - a link to Bernhard Scholkopf’s “Statistical and causal approaches to machine learning” video presentation and the comments of the author of the blog MachineLearningMastery on it.

Data engineering

• Azure Data Factory Preview

Reviews

• Digest of the best resources from DataScienceCentral (December 29)
• The best materials for the week from KDnuggets.com (December 14 - 20)
• Weekly collection of the best materials from R1Soft (December 26)
• The best resources for the week from Data Elixir (№15)
• Freakonometrics # 195 Most Interesting Materials
• The most interesting materials from Freakonometrics # 196
• Freakonometrics # 197 Most Interesting Materials

Previous release: Review of the most interesting materials on data analysis and machine learning №27 (December 15 - 21, 2014)