so recently I came across a problem of predicting the positions of objects from a pulse wave. My biggest concern here is that for each data sample, the number of objects varies. I know that this should be treated as a Multi-output regression problem, but how do I cater to the variation in the number of objects per sample? Also, what would fare better, XGboost or some neural network architecture?

  • $\begingroup$ look for objects detection papers in the CV literature, this was one of the early problems they had $\endgroup$
    – Alberto
    Aug 15 at 10:01


You must log in to answer this question.