Brains seem to require less training data than neural nets.
These deep networks, can they recognize drawings? What about images w/ linear transforms?
-
-
Maybe input should first be rotoscoped/toonified/posterized.
-
Does vision recognize an object looked at directly, stored in cache, thus avoiding need to do un-translation? That doesn't handle rotation.
- 4 more replies
New conversation -
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.