Monthly Archives: April 2019

The creative brain

I just finished the second book on the brain by Dick Swaab. I do not think the English translation has come out yet but if you read Dutch, here you have a reference about it.
This time Swaab focuses, as the Dutch title indicates, on creativity on a general scale: how it is generated, how it is shaped by our genes, by the way children develop in their mother’s wombs, by every single thing that happens to them, to us, until our deaths.

The book is written with the usual dry Dutch humour. It has lots of references to the ailments and quirks of artists, scientists and other people.

The book can become very technical but for someone really interested in the brain, it is a trove of information. It has very good references and a really complete index.

The only thing I wish could have been done better is the images on the different brain parts – there are several small pictures mostly at the start and at the end of the book. Thinking about this I thought it could be good to have something like an online search where you can enter terms about the brain and a 3-D-like visualization rotates, gets zoomed in o or out. That would be the perfect addition for this book. But perhaps I am asking too much. It would be a nice application, though, for people like me, a layman, who want to understand a bit more about our brains.

Testing Python

Professionally I started work using C++ and from there started to go more and more into Java and from there, without leaving it, moving more and more to Python. One of the things I discovered with Python was how little there was on structuring compared to Java. The other thing I found was that I found less information on possibilities for testing than in the Java world.

Percival’s book Test-Driven Development with Python has been an excellent help to getting fast on track using more than basic possibilities for proper testing in this language. A great thing this book does is to help you get a Django project up and running.

Take a look at the book’s site here. It is really good.

Natural Language Processing with TensorFlow by Ganegadara

I actually started to read this book last year. I went through most of it and experimented a lot but had no time to write. I finally read the last chapter, which I had somehow put off. All in all, it is a useful book on using TensorFlow for NLP.

It offers a good exploration of what Word2Vec is. It goes on to CNNs first with image recognition and then with sentence classification, then it does a good initial cover of LSTMS and finally it touches very briefly some trends.

I think I would have skipped the NLP introduction, but then I have worked on NLP almost all of my life. Ganegadara should not have gone so long on WordNet etc. As much as it was an usual tool, it still might be, a paragraph would have been enough.

It was a pity the last part, the one I left until now on trends, was so short but then the technology and even the basics on what deep learning is about are changing so fast!