Hacker News new | comments | ask | show | jobs | submit login

Thanks for the tldr. This sounds rather a lot like a tree based method. How fair is that analogy?





It seems fair to me, in the sense that they are effectively constructing a kind of decision tree. There may be some subtle-yet-significant differences, but they don't contrast their model with other decision trees in the paper.



Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact

Search: