Hi,<p>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.<p>Best,
Wiktor
For neural nets, consider Bengio's book: <a href="http://www.iro.umontreal.ca/~bengioy/dlbook/" rel="nofollow">http://www.iro.umontreal.ca/~bengioy/dlbook/</a><p>For something lighter but insightful, Pedro Domingo's The Master Algorithm is quite fun.<p>A great number of classes are now available online. I prefer the Stanford classes. <a href="http://cs229.stanford.edu/" rel="nofollow">http://cs229.stanford.edu/</a> and <a href="http://cs224d.stanford.edu/" rel="nofollow">http://cs224d.stanford.edu/</a> are good places to start. There are more.
I have recently wrote an article collecting the best AI resources:<p><a href="https://medium.com/@rayalez/best-deep-learning-resources-76b24c67f9e" rel="nofollow">https://medium.com/@rayalez/best-deep-learning-resources-76b...</a><p>Specifically, I would reccommend AIMA as the best introduction to AI in general, and a fantastic video course from Berkeley:<p><a href="https://www.youtube.com/channel/UCshmLD2MsyqAKBx8ctivb5Q/videos" rel="nofollow">https://www.youtube.com/channel/UCshmLD2MsyqAKBx8ctivb5Q/vid...</a><p>and also Andrew Ng's course on coursera:<p><a href="https://www.coursera.org/course/ml" rel="nofollow">https://www.coursera.org/course/ml</a><p>For neural networks there's an awesome course by Hinton:<p><a href="https://class.coursera.org/neuralnets-2012-001/lecture" rel="nofollow">https://class.coursera.org/neuralnets-2012-001/lecture</a><p>and UFLDL tutorial:<p><a href="http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutorial" rel="nofollow">http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutori...</a>
A lot of people are suggesting some bad things.<p>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.<p>The AIMA book <i>is</i> 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 <i>not</i> a book on machine learning, even if it talks a bit about machine learning.<p>The Deep Learning book that people mention is <i>not</i> an introductory book on the subject of neural networks or machine learning.<p>Your best bet is Andrew Ng's Coursera course as an introduction to ML and neural nets.
For AI, I think this is still the Bible: <a href="http://aima.cs.berkeley.edu/" rel="nofollow">http://aima.cs.berkeley.edu/</a><p>Neural networks are moving fast. A notable attempt featuring one of the heavyweights, under preparation: <a href="http://goodfeli.github.io/dlbook/" rel="nofollow">http://goodfeli.github.io/dlbook/</a><p>Meanwhile there is this recent review by the three main suspects: <a href="http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html" rel="nofollow">http://www.nature.com/nature/journal/v521/n7553/full/nature1...</a>
For NN from scratch, there's nothing better than this book:
<a href="http://neuralnetworksanddeeplearning.com/" rel="nofollow">http://neuralnetworksanddeeplearning.com/</a>
Jeff Heaton has written a slew nice AI related books<p><a href="http://www.heatonresearch.com/book/index.html" rel="nofollow">http://www.heatonresearch.com/book/index.html</a><p>"Introduction to the Math of Neural Networks" is a really great book to start with if your math skills are on college algebra level.