This page is my attempt to build a collection of all the things that seem to be interesting and helpful. This are useful web resources, must-read books, amazing comics and even more. If you’ll find there something you like, I’ll consider my mission succeeded.
-
Web resources
In our internet age pretty everything is available online.-
The most comprehensive russian resource for machine learners.
-
Awesome social network for researchers with its own citation manager, which allows to share, read, comment and sync papers (and many more).
-
StackOverflow for ML people.
-
-
Educational content
Lectures, courses, educational videos.-
Graphical models in computer vision and signal analysis. Segmentation and denoising with MRF, HMM for signal analysis, active shape models. In Russian.
-
As title says, it's all about bayesian methods in machine learning. A lot of attention is given to sparse bayesian learning (RVM etc). And I especially like the "campaign against illiteracy" section at the the beginning of each presentation. In Russian.
-
Wonderful presentation about clear thinking, easy writing and quick learning.
-
"Great Ideas in Theoretical Computer Science" MIT course. It's a great introduction into computability, reducibility, complexity theory, PAC learning, quantum computing and many more.
-
-
Blogs
The best thing about blogs is that they usually have links to other blogs. Oh, you can also find some interesting things there.-
Blog of Eric Lippert, on of the developers of the C# language. He likes to show how tiny changes in the language design can produce "butterfly effect" and how difficult language design decisions can be.
-
-
Other
All the things that don't fit into remaining categories.-
The xkcd webcomic. My source of fun and pleasure three times a week.
-
An epic novel about life of Bertrand Russell, in the format of a comic book.
-
Contains both geeky jokes and jokes about dicks. Perfect mix.
-
-
Software
It's not a hardware-
C++ library for graph-cut based energy minimization with MATLAB wrapper.
-
Best .NET framework for Bayesian inference our world has ever seen.
-