I was wondering whether we could list machine learning winning methods to apply in many fields of interest: NLP, image, vision, medical, deep package inspection, etc. I mean, if someone will get started a new ML project, what are the ML methods that cannot be forgotten?

  • $\begingroup$ Hi, this topic is very broad. Please revise your question to be specific to machine learning methods in one field. A list for every field is too broad for this site. $\endgroup$ – sheldonkreger Jan 15 '15 at 20:26
  • $\begingroup$ I apologize for asking such obvious question, but the answer from @javierfdr was exacly the confirmation which I wanted. Anyway, please tell me what might I do. Is a case to delete the my question? Thanks in advance! $\endgroup$ – fabraz Jan 17 '15 at 15:37

The question is very general. However, there are some studies being conducted to test which algorithms perform relatively well in a broad range of problems (I'll add link to papers later), concerning regression and classification.

Lately Random Decision Forests, Support Vector Machines and certain variations of Neural Networks are being said to achieve the best results for very broad variety of problems.

This does not mean that these are "the best algorithms" for any problem, that does not exist, and actually is not very realistic to pursue. Also it must be observed that both RDF and SVM are rather-easy methods to initially grasp and obtain good results, so they are becoming really popular. NN have been used intensively since couple of decades (after they revived), so they appear often in implementations.

If you are interested in learning further you should look for an specific area and deal with a problem that can be solved nicely by machine learning to understand the main idea (and why is impossible to find the method).

You will find common the task to try to predict the expected behavior of something given some known or observable characteristics (to learn the function that models the problem given input data), the issues related to dealing with data in high-dimensional spaces, the need for good quality data, the notable improvements that can give data pre-processing, and many others.

  • $\begingroup$ Thanks @Javierfdr ! I tought that would not have such method. I've already searched at acm, ieee, elsevier, data direct, and so., but even so, I decided to ask here to confirm such expectation. If we narrow to the deep package inspection field, would you recommend any particular method? $\endgroup$ – fabraz Jan 17 '15 at 12:56
  • $\begingroup$ Could you please reply with the papers you've mentioned? $\endgroup$ – fabraz Jan 17 '15 at 15:39
  • $\begingroup$ @fabraz This post I published could be helpful for your question datascience.stackexchange.com/questions/4914/… $\endgroup$ – Javierfdr Jan 20 '15 at 15:28
  • $\begingroup$ it is hard to generalize that random forest and svm gives better results. In my project once I observed that implementing Random forest results in over fit while Logistic regression gave me perfect solution. $\endgroup$ – CodeMaster GoGo Oct 9 '18 at 10:58

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