what book about neural networks or AI in general would you recommend? Which one is the best to learn about this topic from scratch? It would be awesome if it contained also information about the latest discoveries from this field.
For something lighter but insightful, Pedro Domingo's The Master Algorithm is quite fun.
A great number of classes are now available online. I prefer the Stanford classes. http://cs229.stanford.edu/ and http://cs224d.stanford.edu/ are good places to start. There are more.
Specifically, I would reccommend AIMA as the best introduction to AI in general, and a fantastic video course from Berkeley:
and also Andrew Ng's course on coursera:
For neural networks there's an awesome course by Hinton:
and UFLDL tutorial:
Some people might take issue with this, but as far as resources/classes/research groups in academia/textbooks go, AI != machine learning. And neural networks are a subset of machine learning.
The AIMA book is the best introduction to AI, but only to traditional AI, which consists mostly of planning/search/inference algorithms (brute force algorithms, albeit clever brute force algorithms). It is not a book on machine learning, even if it talks a bit about machine learning.
The Deep Learning book that people mention is not an introductory book on the subject of neural networks or machine learning.
Your best bet is Andrew Ng's Coursera course as an introduction to ML and neural nets.
Neural networks are moving fast. A notable attempt featuring one of the heavyweights, under preparation: http://goodfeli.github.io/dlbook/
Meanwhile there is this recent review by the three main suspects: http://www.nature.com/nature/journal/v521/n7553/full/nature1...
Also, Hugo Larochelle videos are remarkable, though a bit tougher to understand.
"Introduction to the Math of Neural Networks" is a really great book to start with if your math skills are on college algebra level.