I recently read through most of Learning Bayesian Networks. I have been using BNs for a while now they are what neural networks should be. I read this book because I wanted to learn more theory. It’s a weird thing that these days you don’t need to know the theory behind how everything works in order to use it. For example OpenBayes and many other libraries allow you to dive into data processing.

That’s the great thing about open source, that there are libraries there for just about everything allowing you to create your application much quicker. For example I would never want to develop a BN from scratch, but for stuff like machine learning it’s necessary to know what is going on in the background especially for when things go wrong.

I don’t usually do blog posts about books I read, but it has been a while since I read a “textbook,” closest thing recently was Neural Networks in Finance. I need to say I always preferred books which are closer to practice than theory.