-
-
Replying to @an_interstice
Thanks for this pointer! Am wondering whether to write a post about it.
1 reply 0 retweets 0 likes -
Replying to @Meaningness
It's interesting. I think the takeaway is "the easiest way to solve static image classification is via textures", rather than a fundamental limitation of neural nets. (evinced by, they can make neural nets do shape recognition when explicitly trying to do that)
1 reply 0 retweets 1 like
Right, I think what we learned is that you can solve the image labeling problem using texture, and also that you can learn texture features using convolutions plus probably a very few layers (one?) of ANN. Whether DLs can do much with shape remains to be seen—clearly some, though
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.