Letting neural networks be weird • Hacker News Board

Re: Letting neural networks be weird

#21

Post by adrianN » Fri, May 25, 2018, 1:06 PM UTC

amelius wrote: post #20

AnIdiotOnTheNet wrote: post #11

> Sometimes I think the surest sign that we’re not living in a computer simulation is that if we were, some microbe would have learned to exploit its flaws. What makes the author so sure that it hasn't? We can only take the workings of the universe for what they are. We have no context with which to determine what is a flaw and what is just physics. One could say that quantum tunneling looks a hell of a lot like a co…

Also: if the effects of the bug were obvious, the creator would have fixed it.

Unless we're running on some forgotten machine in a closet somewhere.

Re: Letting neural networks be weird

#22

Post by chimprich » Fri, May 25, 2018, 1:23 PM UTC

Most of the examples actually come from the unexpected behaviour of evolutionary algorithms.

My favourite example of such (and it doesn't look like it made it into the paper the article is based on) was an attempt to create a random number generator via a genetic algorithm that controlled the development of an electronic circuit. The unexpected way the algorithm solved the problem was to produce a radio.

Edit: I may have been thinking of the result reported this paper. http://people.duke.edu/~ng46/topics/evolved-radio.pdf . If so, the goal was to build an oscillator rather than a random number generator.

Re: Letting neural networks be weird

#23

Post by booleandilemma » Fri, May 25, 2018, 2:15 PM UTC

Sharlin wrote: post #16

colordrops wrote: post #12

These anecdotes remind me of stories where someone asks a genie for a wish, and the genie technically grants it but in a way that is not what the wisher intended. For example, (cribbed from another thread), "I want to be rich". So the genie renames you to Richard. Ironically a very religious buddy of mine claimed that I as a software engineer am in part responsible for releasing a "Jinn", which could have unintended…

Computers are the genies and golems of the fairytales. Stories that demonstrate the folly of confusing what you ask with what you mean are as old as humanity itself, but the stories we now tell are not fictional anymore: we went and built those golems and genies and now share the planet with billions of them!

Your comment reminds me of Neuromancer:

For thousands of years men dreamed of pacts with demons. Only now are such things possible.

Re: Letting neural networks be weird

#24

Post by xaedes » Fri, May 25, 2018, 5:41 PM UTC

In the first example there really _could_ be sheeps, or at least goats. They could cover there quite well.

Like in this video: https://www.youtube.com/watch?v=0izxifsh0MU

Re: Letting neural networks be weird

#25

Post by badminton1 » Fri, May 25, 2018, 6:40 PM UTC

anarazel wrote: post #13

k_sze wrote: post #9

Earlier quoted context omitted.

Well, everything halts then, so that just solved the Halting Problem.

But you need to prove that it halted - to you manager obviously - that's the impossible and stressful part.

Need to explain it to 10 managers if you work in enterprise software.

Re: Letting neural networks be weird

#26

Post by Viliam1234 » Fri, May 25, 2018, 9:24 PM UTC

adrianN wrote: post #21

amelius wrote: post #20

Earlier quoted context omitted.

Also: if the effects of the bug were obvious, the creator would have fixed it.

Unless we're running on some forgotten machine in a closet somewhere.

Any simulation in a sufficiently forgotten machine is indistinguishable from reality.

Re: Letting neural networks be weird

#27

Post by tripzilch » Mon, May 28, 2018, 2:27 PM UTC

anarazel wrote: post #13

k_sze wrote: post #9

Earlier quoted context omitted.

Well, everything halts then, so that just solved the Halting Problem.

But you need to prove that it halted - to you manager obviously - that's the impossible and stressful part.

But is it provable in nondeterministic polynomial stress?