Is Artificial Intelligence Permanently Inscrutable? (2016)

Re:Is Artificial Intelligence Permanently Inscrutable? (2016) by ashelmire on Monday August 27, 2018 @09:17AM (#17851294)

I’m in agreement with you here. This trope that neural networks or other forms of ML are inscrutable is ridiculous. We know exactly what mathematical function is happening at every stage and the goal of the process; we can explain what architectures have the best results, and in some cases a deep understanding of why; with close enough scrutiny, you can probably tell what an individual neuron is doing to a layman (though the scale quickly gets out of hand). Why is it not sufficient to say “we’re using some basic math at a large scale using neural network architectures found to be best suited for the purpose of fitting our task, data, and loss functions?” These architectures are shown to find this sort of information, this is the general overview of how that works. What deeper explanation is desired?

I think the real issue is that tech journalists and laymen don’t know enough to understand. You can’t explain multivariable calculus to someone that doesn’t know algebra. Or option 2/3 are the problem.

[ Parent | on HN ]

Re:Is Artificial Intelligence Permanently Inscrutable? (2016) by gldalmaso on Monday August 27, 2018 @09:42AM (#17851421)

A deeper explanation is often desired when you decide to take your solution to the real world and impact peoples lives.

I'm sure I'm not alone in the fear of living in a (not so far) future dystopia where our driver's licences get cancelled because of our driving behavior caught on traffic cameras. "What did I do that caused it to get cancelled?", "We don't know, better luck next time."

"Your test got flagged for cheating, it's a very sophisticated system with IR vision, audio detection and grade assessment, there's nothing I can do."

"Our theft-preventing camera system says you are suspicious, you're gonna have to go now."

When all we have to respond is "its the algorithm", I don't think much people will be ok with that. Youtube for instance has gone down this rabbit hole and a lot of content creators and users are less than happy to receive that answer.

[ Parent | on HN ]

Re:Is Artificial Intelligence Permanently Inscrutable? (2016) by ashelmire on Monday August 27, 2018 @12:42PM (#17852516)

Those explanations are awful. The reasons are usually pretty simple and sound much more reasonable. The answer is not “I don’t know” in any of those cases - it’s going to be pretty clear that they share some similarity to other cases of theft, cheating, etc, and this will probably be obvious on examination, “our system flags people who are wearing masks” or “these 30 seconds of sounds are almost exactly the intro to song X”. Human review is also useful, but humans make plenty of errors as well (and the response is often “I don’t know why”!).

I’d say these errors are not due to the inscrutable nature of ML but bad communication.

[ Parent | on HN ]

Re:Is Artificial Intelligence Permanently Inscrutable? (2016) by Kalium on Monday August 27, 2018 @11:15AM (#17851968)

People want explanations that are equivalent to the kinds humans offer to explain their behavior. Generally in a cause-and-effect kind of way. Squishies want answers detailed enough to make them feel in control of some part of what's going on. "Because X, so we're doing Y", in theory enables the person to induce different behavior through controlling X.

There are various issues with this desire, including the wrinkle that humans are not always good at explaining their own decisions and we persistently assume we are. But that's neither here nor there. People like feeling in control, and ML tends to expose that they're not.

[ Parent | on HN ]