Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Is it accurate to say that wavelets were a promising avenue of research in the 1990s but interest in them has kind of died because they were obsoleted by CNNs?


Because neural networks can learn a natural basis (on the manifold of natural images). And image compression is not an interesting problem any more.


Not every problem needs a CNN thrown at it.




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

Search: