Review of the most interesting materials on data analysis and machine learning №35 (February 9 - 15, 2015)

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

Survey online courses in mathematics
How to track every roll in the NBA?
Data Scientist in 2015 - entertaining infographics.
Microsoft's computer vision systems are superior to human results - researchers from Microsoft recently released a publication in which they describe a developed system that surpasses human results in image recognition on the popular ImageNet data set.
Deep learning open source modules for the Torch library from Facebook
10 things useful in analyzing data that statistics have taught us
Data Science: Using Python, R, and SQL
Torano vs. Theano - comparing the performance of two popular libraries for Deep Learning.
Two main data analysis tools for comparing different data sets.

To recognize the pictures, you do not need to recognize the pictures.
How to start developing with the field of data analysis - this article from the blog of the popular online learning portal Udacity can help newcomers in their development in the field of data analysis.
Introduction to Python Data Analysis
Data processing with R is a good introduction to data analysis using the R programming language.
Supervised Learning : slides from the Sebastian Raschka report: "An Big Picture".
Build a web service using R and Azure Machine Learning
Visualization of the main component method
Illustration of the principal component method (PCA)
Neural network with NumPy
R for distributed computing - a report on a recent seminar that focused on the use of the R programming language for distributed computing.
A brief introduction to Weka
Deep learning for speech recognition - a list of publications on the use of deep learning for speech recognition.
A series of lessons on machine learning and natural language processing. Lesson 2: Probability

Basic statistics: just about complex formulas
Data Mining Specialization at Coursera - February 9 Coursera, together with the University of Illinois at Urbana-Champaign, launched a new specialization called Data Mining Specialization.
Artistic Intelligence by UC Berkley - On February 6, edX began a very interesting course on the topic of artificial intelligence: CS188: Introduction to Artificial Intelligence. The course is presented by the University of UC Berkley.
The online course “Introduction to Probability - The Science of Uncertainty” from MIT began - on February 3, the regular session of the course on probability theory and presented by the Massachusetts Institute of Technology: Introduction to Probability - The Science of Uncertainty began at edX.
Book: Learning Spark

Inside the Apache Spark - an interesting video on the subject of Apache Spark, Dean Chen (Software engineer, eBay) talks about the inside of Apache Spark.
What awaits Apache Spark in 2015 is an interesting video from the recent motto “What's coming for Spark in 2015”, held at the Databricks office in San Francisco, in which Patrick Wendell from Databricks spoke about the upcoming Apache Spark development plans.
Use Deep Learning to process text
Talking Machines: Episode 4: An Interview with Hanna Wallach is the fourth episode of the Talking Machines podcast series, in this case an interview with Hanna Wallach (Microsoft Research and Professor, Department of Computer Science, University of Massachusetts Amherst), in this episode affected such topics like scaling, size of data sets and others.
Machine learning using F # - in the next release of the podcast "The F # Show" Richard Minerich will tell about his experience in machine learning using the functional programming language F #.

Source: https://habr.com/ru/post/250613/