This is a video discussion and demonstration of the universal LEGO sorting machine built by Australian software engineer Daniel West over the last two years. Using a convolutional neural network, it has the ability to identify every single LEGO piece that's ever been manufactured, even if it hasn't seen the piece itself before. Some more info while I chew a piece in half and see if I can stump it to the point the machine starts smoking and catches fire:
The impressive gizmo stands about 80 centimetres tall, contains over 10,000 individual Lego parts, and 15 motors to move pieces that need to be sorted along a series of conveyor belts. West claims it can process a bucket of jumbled up pieces, grouping 2,927 types of Lego into 18 different bins at a rate of one brick every two seconds.
So it can sort one brick every two seconds. Not bad I suppose, but I feel like I could do it faster. *quickly tosses piece into minifig bucket* "That was a Lincoln Log." *tosses another* "And a marble." I only said faster, I didn't say better.
Keep going for the video, which is actually pretty fascinating if you're into this sort of thing.
Thanks to Mike from Philly, who agrees work artificially intelligenter, not harder.