Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Is artificial intelligence permanently inscrutable?

nautil.us

Post reply on HN
Print view View original

61–69 of 69 posts

Re: Is artificial intelligence permanently inscrutable?

#61

Post by polarix »

empath75 wrote: post #52
colllectorof wrote: post #51

Earlier quoted context omitted.

You're hand-waving a real problem by asserting rather misanthropic ideas with scant justification. Show some child a cat and ask why it's not a crocodile. They will be able to explain it through the differences in shape, color, behavior and other features of those animals. Whether you consider it post-hoc is unimportant. The explanation is still real and relevant. So people can explain their deliberate reasoning. Als…

Most actions people take are not the result of deliberate reasoning. You may be able to explain why a cat is different than a dog, but your brain doesn't go through that categorization process before recognizing a cat.

Right.

We've added instrumentation to our recognition capabilities in order to socialize and gossip about derived categories through language. In addition, we (can sometimes) use the formalized expressions of these categories prepared for socialization to ensure internal consistency.

Artificial neural networks that did something similar could have a number of major philosophical and practical advantages: - enable decentralization of data sets - grow with humans rather than apart from them - enable identifying problematic internal inconsistencies

Re: Is artificial intelligence permanently inscrutable?

#62

Post by kilotaras »

hyperion2010 wrote: post #38

This is not just an issue for neural nets, but also for brains. Our interpretations of our own actions should always be considered posthoc rationalizations in the absence of some falsifiable experiment being conducted to demonstrate the validity of the interpretation. Human brains are excellent at creating a coherent story about the world they experience based on the data at hand, thus we suffer the same kinds of iss…

> Human brains are excellent at creating a coherent story about the world they experience based on the data at hand,

One example of this is Anton-Babinski syndrome [1]. The patient can't see but is completely sure he can.

[1] https://en.wikipedia.org/wiki/Anton%E2%80%93Babinski_syndrom...

Re: Is artificial intelligence permanently inscrutable?

#64

Post by rdlecler1 »

The answer is no. The problem is, is that we don't trim the neural networks of their spurious connections and instead we're stuck staring at these fully (visually) connected layered networks.

Once you start to trim out the spurious connections you start to see that you are left with a logic design with integration/threshold circuits instead of straight binary circuits that we're used to seeing. There are even certain universal network patterns what will emerge to perform different functions just like in binary circuit design.

I wrote a paper about this in 2008 that's now been cited about 150 times. It's using Artificial Gene Regulatory Networks instead of Artificial Neural Networks, but the math is the same and the principle still holds:

http://m.msb.embopress.org/content/4/1/213.abstract

Re: Is artificial intelligence permanently inscrutable?

#65

Post by phaedrus »

rdlecler1 wrote: post #64

The answer is no. The problem is, is that we don't trim the neural networks of their spurious connections and instead we're stuck staring at these fully (visually) connected layered networks. Once you start to trim out the spurious connections you start to see that you are left with a logic design with integration/threshold circuits instead of straight binary circuits that we're used to seeing. There are even certain…

Around 2006 - 2008 I participated in a Research Experiences for Undergraduates program at an AI lab. I used to get into arguments with grad students when I asserted it was intuitively obvious that given a neural network which recognizes two features, it should be possible to extract a trimmed network which recognizes one feature but not the other.

Re: Is artificial intelligence permanently inscrutable?

#66

Post by Joof »

cscurmudgeon wrote: post #21
peterbonney wrote: post #18

Earlier quoted context omitted.

Or: nobody understands exactly how your doctor's brain reaches its conclusion about what's wrong with you, but you still trust it.

It is not like the doctor can explain in English when you ask him for details. Not all.

I have a difficult time getting psychiatrists to do exactly this, so no change here in that area.

Re: Is artificial intelligence permanently inscrutable?

#67

Post by rm_-rf_slash »

peterbonney wrote: post #19
rm_-rf_slash wrote: post #17

Earlier quoted context omitted.

Except human brains are validated by other human brains to be capable of performing a given task. The validations come in many forms with varying degrees of accuracy for the task required. Ex: -college degree (Doctor) -employee referral (engineer) -FizzBuzz (engineer again) -licensing exam score (driver) -popular election (supreme commander of the armed forces)

The same validation scheme(s) can be applied to AI as well. That doesn't mean their inner workings are any more or less penetrable, just that they pass some minimal threshold of competence. E.g., AlphaGo is clearly good at Go. Yet it makes moves that can appear inscrutable to a human expert. (NB: I'm not arguing that inscrutability is or is not an issue for AI systems, just suggesting that third-party validations don…

Exactly. I think trying to validate end-to-end is tail-chasing. Reminds me of Adam Curtis' BBC documentary "The Trap," whrein people create a limited theory of human behavior based on game theory, but the attractiveness of numbers results in the reformation of society to better fit those numbers, even if they don't fully represent human behavior and leave us worse off than before.

It's like trying to create an AI to play chess but the creators focus so hard on keeping it from making moves that result in its losing the queen that they forget that the objective of chess is to win.

Re: Is artificial intelligence permanently inscrutable?

#69

Post by cscurmudgeon »

jerf wrote: post #37
cscurmudgeon wrote: post #22

Earlier quoted context omitted.

So how do we get the first sick volunteers for Dr. Neural Network?

AI's been in medical diagnosis for a long time and many people have been treated by it already. There was a news article a month or two ago from IBM for using Watson to do it, and it struck me as obviously a PR piece because "an AI system diagnosed a patient" is breaking news somewhere circa 1980, not now. Its scientific content was zero.

We are talking about neural networks not general AI.
Post reply on HN