A decade ago, the objective was to have a build farm and do continuous integration (on each commit, build the application and run unit tests). Now, the objective is continuous delivery. This means that the new build is directly put into production. All the major applications are doing this, from Chrome to Spotify. You may not get every version on your machine, but you should consider a build as something you could deploy.

The nice thing is that there are tools to ease this workflow.

Read More

This entry is part 1 of 1 in the series Deep adventures

A few year ago, Packt Publishing contacted to be a technical reviewer for the first edition of Building Machine Learning Systems with Python, and I was impressed by the writing of Luis Pedro Coelho and Willi Richert. For the second edition, I was again a technical reviewer.

Writing is not easy, especially when it’s not your mother tongue, and scientific books are plagued with books that are not that great, with low technical content or bad English (that can be said for novels as well, the worst I ever read probably being the Hunger games series…). Even if I don’t like the books, I know that the authors did their best, having written in the past a book that I can say was not very great in terms of flow. Writing a book always deserves the deepest respect.

Read More

This entry is part 5 of 5 in the series Travelling in LLVM land

LLVM has always intrigued me. Actually, I always thought about one day writing a compiler. But it was more a challenge than a requirement for any of my works, private or professional, so never dived into it. The design of LLVM was also very well thought, and probably close to something I would have had liked to create.

So now the easiest is just to use LLVM for the different goals I want to achieve. I recently had to write clang-tidy rules, and I also want to perhaps create a JIT for Audio Toolkit and the modeling libraries. So lots of reasons to look at LLVM.

Read More

This review will actually be quite quick: I haven’t finished the book and I won’t finish it.

The book was published in August 2015 and is based on OpenGL < 3. The authors may sometimes say that you can use shaders to do better, but the fact is that if you want to execute the code they propose, you need to use the backward compatibility layer, if it's available. OpenGL was published almost a decade ago, I can't understand why in 2015 two guys decided that a new book on scientific visualization should use an API that was deprecated a long time ago. What a waste of time. [amazon_enhanced asin="1782169725" /][amazon_enhanced asin="B01FGMWRO8" /]

Almost 18 months ago, I posted a small post on the first version of this book (http://blog.audio-tk.com/2013/09/04/book-building-machine-learning-systems-in-python/). At the time, I was really eager to see the second edition of it. And there it is!

I had once again the privilege of being a technical reviewer for this book, and I havce to say that the quality didn’t lower one bit, it went even higher. Of course, there is still room for a better book, when all Python module for Machine Learning are even better. I guess that will be for the third edition!

To get the book from the publisher: https://www.packtpub.com/big-data-and-business-intelligence/building-machine-learning-systems-python-second-edition

On other matters, the blog was quiet for a long time, I’m hoping to get some time to post a few new posts soon, but it is quite hard as I’m currently studying for another master’s degree!