Human visual representations are not only translation-invariant (like CNNs), but also symmetry-invariant, & invariant for small rotations.
Show this thread
-
Would you see e.g. identical reading speeds for mirror text and regular text in those kids?
Not sure if that has been tested. But kids can produce mirror version of complex symbols (cursive) upon first trial. It's not gesture memory
-
-
How is not gesture memory? Do the task of writing mirror images yourself, you will basically sketch out the gesture in your mind.
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.