Is there any review paper or something related which presents a taxonomy of all (or subgroup(s)) of classification, clustering, bayesing methods etc.


  • $\begingroup$ You can either find broad shallow taxonomies in textbooks/images on the net, or read in-depths surveys for each topic. In addition to what Adelson posted, there are surveys on feature selection, anomaly detection, etc. as well as surveys for applications to particular topics such as text, images, time series, etc. $\endgroup$ – DAF Nov 15 '17 at 19:02

For supervised techniques in general, I recommend you to read [1], and for clustering [2]. Both are long reviews, but very incisive and rich of information.


[1] Kotsiantis, Sotiris B., I. Zaharakis, and P. Pintelas. "Supervised machine learning: A review of classification techniques." (2007): 3-24.

[2] Berkhin, Pavel. "A survey of clustering data mining techniques." Grouping multidimensional data 25 (2006): 71.

| cite | improve this answer | |
  • $\begingroup$ do you think more than 10 years old surveys will cut in this rapidly advancing field? $\endgroup$ – Aksakal Nov 15 '17 at 18:35
  • 1
    $\begingroup$ I agree with you that this is a rapidly advancing field. However, I understood the question's need for a established taxonomy rather than a state-of-art review. Both surveys explain techniques that are still in use today and are the foundations to understand the new ones. $\endgroup$ – Adelson Araújo Nov 15 '17 at 18:54
  • 1
    $\begingroup$ @Aksakal is there something you are using that was not around 10 years ago? $\endgroup$ – rep_ho Nov 16 '17 at 12:33
  • $\begingroup$ @rep_ho, would you say nothing important happened in past 10 years in ML/AI? that would be an odd thing to claim $\endgroup$ – Aksakal Nov 16 '17 at 13:13
  • $\begingroup$ @Aksakal can you give an example? $\endgroup$ – rep_ho Nov 16 '17 at 13:26

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.