Handwritten Digit Recognition by csavas
Recognizes handwritten digits. Very fast, about 2.5 seconds at 60 fps. Draw into the WALL (thick light-gray) box using INWR (electronics section), anything else will break it. The start button can be clicked WITHOUT switching to sprk.
neural
network
intelligence
number
artificial
electronics
handwriting
subframe
mnist
Comments
-
MrAbsolute 29th Aug 2024
impresive -
JonaHungary 27th Aug 2024
This is the most impressive thing ive seen yet -
MegaKnight86 27th Aug 2024
yep thas good thas some good stuff oooohhh yeah -
Tptnoob1 26th Aug 2024
okay what idiot downvoted -
Personman 26th Aug 2024
Powder toy is turing complete -
XAORESS 26th Aug 2024
for some reason it keeps saying 6 but have my like, it's big brain anyways regardless of the accuracy -
polziet21 25th Aug 2024
My god your an absoulte genius. +1 -
_killer_ 24th Aug 2024
R33sesK1ng: From what I can tell, no, that would make it ten times harder. It uses a databank storing the weights for sections and evaluates the similarity and thus probability for each digit (the piston chambers) and outputs the most probable one. A very simple AI, incapable of learning. But the fact that this was made in a sandbox game is incredible. -
R33sesK1ng 24th Aug 2024
Wait does this use neural learning? -
mawi 24th Aug 2024
This is MAD impressive. Even when coding this in a normal programming language this is extremely impressive. The fact that you did it in Powder toy makes it 10x more impressive. Well done!