<pre><pre>An Amazon engineer has made a cat-powered cat flap to prevent his cat from taking dead animals home

Machine learning can be an incredible addition to a tinker's toolbox, helping to solve that small 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 in dead and half-dead prey in the middle of the night and waking him up.

Hamm gave a nice presentation on this subject at Ignite Seattle, and you can watch one video from his chat above. In short, to prevent Metric from following his instincts, Hamm hung the cat flap in his door to an AI camera (Amazon & # 39; 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 that had been 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 receive a text. (In a beautiful bloom, the system also sends a donation, or & # 39; blood money & # 39; as Hamm calls it, to the National Audubon Society, which protects the birds that kill cats.)

It is a short presentation, but it perfectly illustrates the daily usefulness of AI. As Hamm shows, a little intelligence can go a long way – it can even outwit a cat.