News for hackers. Stuff that matters.
Re:Human-level concept learning through probabilistic progra... by cromwellian on Monday December 14, 2015 @10:45PM (#10735783)
Isn't it the case that human one-shot classification tasks can rely on a pre-existing corpus of concepts that span a richer and broader area?

For example, someone who looks at a segway, won't just see the pixels of a two wheeled vehicle, and that it is axially unlike a bike, but they may have also read articles about it, and know that two wheeled vehicles without peddles or mechanisms for riders to stabilze them, imply the device has a self-stability function.

Thus, a human being could group a segway or unicycle segway type device, with BB-8 style self-balancing/gyro balls that people can ride as chairs. But to do so, they are relying on reasoning about how the device must work, not just image recognition.

I mean, I welcome all of these advances at getting better at recognition tasks, but I still feel like we're producing "Fast Brain" AI, not "Slow Brain" AI.

Re:Human-level concept learning through probabilistic progra... by smackwagon on Tuesday December 15, 2015 @12:59AM (#10736195)
I was thinking this too. I'd be curious if one could even provide a single clear and unambiguous example of something people learn via "one-shot" classification.
Re:Human-level concept learning through probabilistic progra... by choicewords on Tuesday December 15, 2015 @10:09AM (#10738124)
From personal experience, touching a red hot stove. No further classification was needed.