I've only just started looking into Machine Learning, and so far most of the examples I've seen involve starting with a training set of observations, each representing a value for a number of 'features', and using that to train a model - then evaluating the trained model against a second test set of data to allow refinements to the model. The basic operation the model is asked to do is to predict the value of one feature given others.

When talking about art (by which I would include music, poetry, etc), we can no longer assert that things are correct - but perhaps we could isolate a number of subjectively-judged features, such as whether a work is 'mysterious' or 'joyful' to a particular human judge, and then train the model to our judge's taste. However, The problem here would seem to be that having a human being add judgement features to each of our data points sounds like a very slow task, and it might often be impractical to get to the number of 'assessed works' that would allow the model to be trained.

How could the process of training a model to produce art of a certain 'taste' be done in a practicably short space of time?


1 Answer 1


You will need a large training set to be able to train your machine to produce subjectively pleasant 'artistic' output.

If you can't produce your own dataset with real people, you can try the following:

  • search for existing datasets on the internet
  • produce a new dataset using a spider bot that perform mining of artistic output on websites that have voting features
  • use crowdsourcing

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .