There are two textbooks that I most love and am most afraid of in the world: Introduction to Algorithms by Cormen et al. and Artificial Intelligence: A Modern Approach by Norvig et al. I have started the "AI: A Modern Approach" more than once, but the book is so dense and full of theory that I get discouraged after a couple of weeks and stop.

I am looking for a similar AI book but with an equal emphasis on theory and practice. Some examples of what I am looking for:

  • The Elements of Statistical Learning by Tibshirani et al. (detailed theory)

  • An Introduction to Statistical Learning: With Applications in R by Tibshirani et al. (theory+practical)

  • Digital Image Processing by Gonzalez et al. (detailed theory)
  • Digital Image Processing Using MATLAB by Gonzalez et al. (theory+practical)

In addition to the books already mentioned, I would like to recommend to you some that helped me understand the basics and guided me through my first AI / CI implementations.


Firstly, you should be clear about on which subject you want to study.

AIMA deals with conventional ai algorithms like path planning, logic etc.

Elements of statistical learning is a machine learning book which covers most of the machine learning algorithms you will come across (spare deep learning). digital image processing is an entirely different field which deals with processing images (contouring, reconcstruction, filters etc.)

If you want a clear cut ai book AIMA is hands down the best, but you cant read it one go, it is more like a referance textbook. instead it is much better to enroll in an online course and follow the book as a supplement. (check udacity)


It is not a book in the classical sense, but Google Scholar makes a great job as an introduction to Artificial Intelligence. The website was founded with the aim to give access to a large variety of educational resources from subjects like Statistics, path planning, machine learning and digital image processing. The main advantage over a conventional book is, that it get updates continuously, it is for free to the reader and can be cited in a scientific context.

In contrast to a classical book, Google Scholar is not the book itself but is only a portal to get access to manuscripts which are already there. It can be seen as frontend for learning resources all over the world. Most papers are written in English, but there are some exceptions written in French, Chinese and Greek. The disadvantage is, that at least half of the content is not accessible because of copyright reasons of the publishers, so it can happen that the student sees only a snippet but not the content. So from a negative perspective, Google Scholar is a marketing platform to support the business of Elsevier and Springer.

What is different compared to studying a book like AIMA is, that it is not possible to read Google Scholar linear from frontcover to back. There is no logical structure, instead the manuscripts are arranged in a collage. The best way to benefit from the chaos is to create a note list with key words. For example, the user want's to know something about Statistical Learning, so he first creates a note:

- Statistical Learning

Then he founds in paper 2, that Deeplearning sounds also interesting, so the next keyword on his list is:

- Statistical Learning
- LSTM network (invented by Schmidhuber et. al)

The notes can be annotated by personal insights and provide a personal history in the search process. After some weeks, the user has created a long list of search keywords which are ordered chronological and make it easy to go back to previous papers he has read. This helps to navigate in the full-text-corpus. From a certain point of view, the user has to create his own “table of contents” from the Google Scholar content. So the reading process is a bit different from a classical textbook.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.