The difference in clasterisation task is, that the classes of objects are not given , but must be determined from the dataset.

Usual usecase for NN is like having images of cats and dogs, and the right answers in form like [1,0] for cat, [0, 1] for dog , to backpropagate from those results. If the right answers are unknown , how NN will learn then? Also there might be unknown amount of classes and the output vector could "grow" somehow

  • 3
    $\begingroup$ It looks like you are asking about using Neural Networks for unsupervised learning, and specifically for clustering (clasterization is, I think, an older and disused term). See this question on CV.SE for the details of using NN's for this: stats.stackexchange.com/questions/140148/… $\endgroup$ – John Doucette May 23 at 3:06
  • 1
    $\begingroup$ no, its because of my english, thanks for the tip . $\endgroup$ – user8426627 May 23 at 11:17

Your Answer

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

Browse other questions tagged or ask your own question.