I am trying to figure out the concept of "input space" in the context of machine learning.

Wikipedia is using this term and does not give a definition or explanation of it.

This post gives a definition of "input space". (Please give a more appropriate definition or explanation if needed)

The "input space" is just all the possible inputs.

Consider the Iris flower data set, is the "input space" of this dataset $$R^4$$ or something like $$X^4, 0<X<R$$

  • $\begingroup$ This "definition" is too broad for your question to be answerable: the "input space" is whatever you might care to specify. It's determined by far more than the set of data you might already have, including alternative possibilities you contemplate for the data, what might be implied by any probabilistic assumptions you make, the prediction procedures you might be applying, and the purposes of your analysis. $\endgroup$ – whuber Sep 16 '19 at 12:03
  • $\begingroup$ @whuber Thanks for your comment. Please give a more appropriate definition or explanation if needed. $\endgroup$ – whnlp Sep 16 '19 at 12:21
  • $\begingroup$ It's not my role to formulate your question for you: you must clarify for us what you need to know. $\endgroup$ – whuber Sep 16 '19 at 12:45

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.