HSE Big Data Systems Blog

Are you new to bioinformatics? Perhaps, you did not plan to get acquainted with biology-related sciences but, by studying the data science, this is worth doing! Why?? - Well, this application field is quite specific, yet very promising and diverse for a person not afraid of math and programming, and in addition, it is growing rapidly!

Today talk by scientist and entrepreneur Riccardo Sabatini will show you how it comes possible to predict things like height, eye color, age and even facial structure — all from a vial of blood, only by reading the human genome: youtube.com/watch?v=s6rJLXq1Re0.

In fact, tremendous opportunities are open to us: we already have the necessary tools, now it is time to move from theory to practice since investigations are not limited to solely phenotype predictions, and here machine learning will let us progress to another applications and advancements, for example, the area of personalized medicine...

How to read the genome and build a human being | Riccardo Sabatini Secrets, disease and beauty are all written in the human genome, the complete set of genetic instructions needed to build a human being. Now, as scientist an...

Hey, guys, what are your plans for tomorrow night? The thing is tomorrow, June 23, in the Moscow office of Yandex the regular Moscow Python Meetup will be held. The program includes three presentations. In addition to traditional (for meetup community) stories about new technologies, they will talk about the concept of open data, and will show what tasks it offers to Pythonists. Since the event is very popular, the registration was closed almost immediately, however, the webcast is going to be held here: youtube.com/watch?v=dMafO5-HsTM

Program of the event:
7 P.M. (UTC+3:00) Telegram Bot API 2.0 - what's new?? Speaker: Bogdan Evstratenko, Yandex
7:40 P.M. (UTC+3:00) Push, or how to discharge a strange phone. Speaker: Alina Baymasheva, Rambler & Co developer
8:20 P.M. (UTC+3:00) What Pythonists can do with Open data? Speaker: Elena Nikitina, Analytical Centre under the Government of the Russian Federation

Get connected and do not miss the fun!

Hurray!!! Researchers at MIT have demonstrated a deep learning algorithm that has effectively learned how to predict sound. When shown a silent video clip of an object being hit, the algorithm can produce a sound for the hit that is realistic enough to fool human viewers. Nevertheless, researchers say that there’s still room to improve the system. For example, if the drumstick moves especially erratically in a video, the algorithm is more likely to miss or hallucinate a false hit. It is also limited by the fact that it applies only to “visually indicated sounds” — sounds that are directly caused by the physical interaction that is being depicted in the video.

“When you run your finger across a wine glass, the sound it makes reflects how much liquid is in it,” says CSAIL PhD student Andrew Owens, who was the lead author on an upcoming paper describing the work. “An algorithm that simulates such sounds can reveal key information about objects’ shapes and material types, as well as the force and motion of their interactions with the world.”

Actually, the advance could lead to better sound effects for film and television and robots with improved understanding of objects in their surroundings.

Check the video and see (hear?) everything with your own eyes: youtu.be/0FW99AQmMc8
Link to original MIT article: news.mit.edu/2016/artificial-intelligence-produces-realistic-sounds-0613

EURO 2016 is getting on 🔥!
Today we bring some EURO predictions by several IT-giants – they wouldn’t fascinate you with originality (however, that’s not the statistics feature, is it?) but still are really interesting.

Yahoo and Tumblr have analyzed 20 bln sport blogs since the beginning of the year plus 4 years of statistics and came out with a full prediction of all the matches: vk.cc/5h1SNc

Microsoft using its Bing has predicted the group stage (vk.cc/5h266I) and the play-off round (vk.cc/5h26fH) results. By the way, back in 2014 Microsoft succeeded to predict all the matches outcomes without any mistake…

Goldman Sachs have also prepared a prediction for the match outcomes and the probabilities of advancement as well. No spoilers except saying that our Russian national team has only 2,6% probability of winning the EURO: vk.cc/5h1Tdx

Another pack of predictions by the Belgian Bisnode company – presented as nice infographics! vk.cc/5h1WQD

German analytic agency Blue Yonder, founded by an ex-CERN scientist has predicted a top of probable champions: vk.cc/5h24dU. There are no surprises, and no detailed algorithm description, but the data used covers last 100 years!

Statistical Natural Language Processing in Python or How To Do Things With Words. And Counters. or Everything I Needed to Know About NLP I learned From Sesame Street: nbviewer.jupyter.org/url/norvig.com/ipython/How%20to%20Do%20Things%20with%20Words.ipynb

Sounds amusing, doesn’t it?! So, let’s check, how NLP is performed in Python on the example of a text file. This project covers practically everything: from the Zipf's law and spelling correction to word segmentation and evaluation results. This example appears to be very useful for the learning process, your course work, or simply as a guide for further studies!

Learn about new functions, check your skills and… do not forget cookies!