We have some of the Internet’s hacking elite judging The Hackaday Prize, and that means they can’t enter any projects into the prize. All the better for everyone else, we suppose. One of the judges, [Sprite_tm], is a resourceful guy and when it comes to judging the entries for The Hackaday Prize, he’s going to do what comes naturally to him: build a machine to automate the task.
[Sprite]’s plan for the JudgeTron 9001 is to use neural networks embedded in biological specimens to do the judging for him. Honestly, we really appreciate the effort he put in to this; biohacking is really in vogue right now, and we do love the classic throwback to the AI renaissance here. It certainly doesn’t hurt that he’s using a Raspberry Pi and an Arduino for this project, either.
Grabbing a touchscreen LCD and a few other parts out of his junk drawer, [Sprite] quickly whipped up a project that would display entries to The Hackaday Prize to the biologically embedded neural nets. These nets needed a little bit of encouragement to select winning entries, so a ‘feed’ back mechanism was laser cut out of acrylic, mounted to a servo, and filled with positive reinforcement.
The software running on the Pi crawls through the list of entries to The Hackaday Prize, extracting images from each one. The plan was for the biological neural nets to select winning entries and be rewarded via the feedback mechanism. These neural nets proved to be very sensitive to the sound of the servo gears of the feedback mechanism, and [Sprite]’s attempt at finding a winning entry with his creation has so far proved unsuccessful. Still, there’s a video of it in action, you can check that out below.