Human visual representations are not only translation-invariant (like CNNs), but also symmetry-invariant, & invariant for small rotations.
Show this thread
-
The second point is exemplified by "mirror writing" seen in kids learning to write - they store letter shapes in an orientation-indep way.pic.twitter.com/I3SCaq84TW
Show this thread
-
-
If you had to store images as muscle movement controllers to direct brush strokes to approximate them, would be closer to these invariances.
-
No, the invariance is in the visual representation. No connection with remembering gestures and no link to writing/drawing practice.
- Show replies
New conversation -
-
-
Is there any research on DNN exhibiting similar symmetries?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.