I study AI by myself with the book "Artificial Intelligence: A Modern Approach". I've just finished the chapters about the Bayesian network and probabilities, and I found them very interesting. Now, I want to implement different algorithms and test them in different cases and environments.

Is it worth it to spend time on these techniques?


*AI, A Modern Approach," was given that title to break from previously narrow approaches to duplicating desirable qualities of human thinking.

Although Bayesian networks require somewhat resource intensive computational elements, the importance of Bayesian inference and probability are still of paramount importance in that some of the highest scientific thinking require mastery of them. Furthermore, developing in silicon dies (or possibly graphene nanites) the machinery to perform elementary probability computations in massively parallel architectures may arise over the next few decades. The use of video DSP circuits to implement ANNs is a notable segue into this kind of development.

I would not dismiss the techniques you just read about. If your intention is to capitalize on the recent crazes, you may enter the river of wannabees chasing every current trend, implement many systems that other people will rewrite later, and have a meaningless yet profitable career. I would recommend following your inquisitiveness instead.

  • 1
    $\begingroup$ Thank you, I'm curious but if it's is important I prefer stay focus on what I'm learning now because I am not yet comfortable with all these notions. Personally I have a bachelors Degree (3 years) and learn by curiousity. I don't really know in wich domains I'll use these technics I think about games for fun and for a start. $\endgroup$
    – Kaizokun
    May 30 '18 at 8:35
  • $\begingroup$ Expanding your vocabulary and learning notation conventions run parallel to expanding your comprehension of the concepts. Keep reading and you may return to things you read before and find new information you missed the first time. That happens to me all the time. $\endgroup$ Jun 1 '18 at 23:49
  • $\begingroup$ I agree there are so much concepts and information, it's impossible to remember everything. $\endgroup$
    – Kaizokun
    Jun 2 '18 at 8:19

The chapters for Bayesian Networks are:

  1. Quantifying Uncertainty
  2. Probabilistic Reasoning
  3. Dynamic Bayesian

don't forget:

  1. Naive Bayes, hidden variables, Markov

Maybe helpful:

. Are We Going in the Right Direction? ... p.1049

If you find them interesting then invest more time to it. You might improve them and break new scientific ground.

Recent trend goes Deep Convolutional Neural Networks (ex: AlphaGo)

  • $\begingroup$ Why don't you mention the chapters 16 and 17? The concepts covered in these chapters seem very important. I found them very interesting to design agents for different kinds of environments. $\endgroup$
    – Kaizokun
    Jun 5 '18 at 15:17

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.