Wikipedia defines machine learning as the "field of computer science that gives computers the ability to learn without being explicitly programmed". A common example of a problem which machine learning is good at solving would be for example image categorization. It would presumably be incredibly difficult to write an explicit algorithm that would analyze pictures pixel by pixel and tell apart dogs from cats, for example, so it's easier to just use some sort of supervised learning strategy and feed it a lot of pre-categorized pictures of cats and dogs.

Now, how to I name this category of problems (e.g. telling dogs from cats)? Is there a particular name?

PS: In case this is relevant, I'm not a specialist in machine learning. My degree is in computer engineering and I work as a software developer but I'm doing a master's in analytic philosophy and I think this concept would be helpful for an essay I have to write for philosophical logic.


closed as off-topic by Aryeh, Kaveh, D.W., Andrej Bauer, Jeffε Jan 1 '18 at 5:07

This question appears to be off-topic. The users who voted to close gave these specific reasons:

  • "Your question does not appear to be a research-level question in theoretical computer science. For more information about the scope, please see help center. Your question might be suitable for Computer Science which has a broader scope." – Aryeh, D.W., Jeffε
  • "Questions must demonstrate a minimal understanding of the problem being solved. Tell us what you've tried to do, why it didn't work, and how it should work. See also our question checklist." – Kaveh, Andrej Bauer
If this question can be reworded to fit the rules in the help center, please edit the question.


[Too long for a comment.] The question will probably get downvoted and closed, but before that happens, let me try to explain why. This is theoretical computer science, where we deal with formally statable and provable claims. A claim such as, "the problem of telling cats apart from dogs is only solvable by machine learning" is not a formal statement. Meaning: as stated, it's not even true or false, just ill-defined. Worse yet, I don't think it admits any meaningful formalization.

Now just so you don't walk away empty-handed, there is a whole host of problems where machine learning currently outperforms all other approaches. Certainly object recognition is one of those problems.


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