Machine learning can be an incredible addition to any tinkerer’s toolbox, helping to fix that little problem in life that no commercial gadget can handle. For Amazon engineer Ben Hamm, that problem was stopping his “sweet, murderous cat” Metric from bringing home dead and half-dead prey in the middle of the night and waking him up.
Hamm gave an entertaining presentation on this subject at Ignite Seattle, and you can watch a video of his talk above. In short, in order to stop Metric from following his instincts, Hamm hooked up the cat flap in his door to an AI-enabled camera (Amazon’s own DeepLens) and an Arduino-powered locking system.
Training images collected and hand-labeled by Hamm. (Yes, those numbers are in the thousands. That’s a lot of data sorting!)
The camera was loaded with machine vision algorithms trained by Hamm himself. They identified whether Metric was coming or going and whether he had prey in his mouth. If the answer was “yes,” the cat flap would lock for 15 minutes and Hamm would get a text. (In a nice flourish, the system also sends a donation, or “blood money” as Hamm calls it, to the National Audubon Society, which protects the birds cats love to kill.)
It’s a short presentation, but it perfectly illustrates the everyday utility of AI. As Hamm shows, a little bit of intelligence can go a long way — it can even outsmart a cat.