“We’re just starting to learn how to look for, in machine learning, what’s called anomaly detection,” says Dan Wertheimer, chief scientist for SETI at the University of California at Berkeley. “In anomaly detection, you classify things — ‘this is a curved signal, this is a sinusoidal signal, this is a pulsed signal’ — and if it’s not one of those things, it’ll say, ‘Hey, I found something that’s not following all these categories, this is an anomaly.’ It will alert you, and you’ll take a look at it and see if it’s interesting. We are not doing that now, we’re learning how to do that.”
