News for hackers. Stuff that matters.
Re:Artificial Intelligence Is Already Weirdly Inhuman by seiji on Thursday August 06, 2015 @06:19PM (#10019859)
that's not the task we trained it for!

Yes, exactly. We're not training consciousness networks. That's not even a goal of all this research. We're training dumb high-speed classifiers.

How might we train an ANN to explain its reasoning?

There are networks that exist today that'll happily explain an entire scene to you (the whole "this picture contains a pizza sitting on an oven in a kitchen and there is a dog in the corner"), which is closer, but still just pairwise training. The "thought" process isn't recurrent or turing complete so it can't make progress on its own.

Re:Artificial Intelligence Is Already Weirdly Inhuman by chriswarbo on Friday August 07, 2015 @08:10AM (#10021972)
> There are networks that exist today that'll happily explain an entire scene to you (the whole "this picture contains a pizza sitting on an oven in a kitchen and there is a dog in the corner")

I was thinking more along the lines of: "This picture contains pizza. This is because there is an ellipse which appears to be covered with cheese and pepperoni. I say that because the dominant colour is yellow and there are elliptical patches of a more reddish colour. ..." and so on, down to the pixel level.

We can kind of get this by running the networks backwards, but it's not really deductive reasoning; for example, we can't correct the network by saying "that yellow ellipse covered with red ellipses is actually a pile of vomit", and watch that knowledge propagate through the weights. Instead, we have to re-train with more examples of pizzas and vomit.

Re:Artificial Intelligence Is Already Weirdly Inhuman by poizan42 on Thursday August 06, 2015 @07:57PM (#10020230)
> There are networks that exist today that'll happily explain an entire scene to you (the whole "this picture contains a pizza sitting on an oven in a kitchen and there is a dog in the corner"), which is closer, but still just pairwise training. The "thought" process isn't recurrent or turing complete so it can't make progress on its own.

Aren't those generated by RNNs, which are Turing complete?