(no subject)
Sep. 24th, 2018 02:10 am![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
timeletshttps://www.quantamagazine.org/machine-learning-confronts-the-elephant-in-the-room-20180920/
As a separate thought, it shows the value of truth: one can afford efficient feed-forward strategy in high-trust situations.
Most neural networks lack this ability to go backward. It’s a hard trait to engineer. One advantage of feed-forward networks is that they’re relatively straightforward to train — process an image through these six layers and get an answer. But if neural networks are to have license to do a double take, they’ll need a sophisticated understanding of when to draw on this new capacity (when to look twice) and when to plow ahead in a feed-forward way. Human brains switch between these different processes seamlessly; neural networks will need a new theoretical framework before they can do the same.
...
Earlier this month, Google AI announced a contest to crowdsource image classifiers that can see their way through adversarial attacks.
As a separate thought, it shows the value of truth: one can afford efficient feed-forward strategy in high-trust situations.
