Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[scrdest]

Genetic evolution took billions of years to evolve humans, human's neural networks took only 10,000 years after learning agriculture to conquer Earth.

The two approaches may perhaps be optimized to different goals.

For example, the human neural networks are prone to missing results that work, but are functional.

There was an early experiment in hardware evolution by Dr. Adrian Thompson with FPGAs that had to recognize two different frequency signals - the end-result had five out of thirty-seven logic gates that were completely disconnected from the whole thing, but taking them out made it stop working, and was working with the individual chips' nuances and non-binary signals.

You'd never get this kind of solution via a deliberately engineered system.

[forsaken1111]

Genetic evolution took billions of years to evolve humans, human's neural networks took only 10,000 years after learning agriculture to conquer Earth.

The two approaches may perhaps be optimized to different goals.

For example, the human neural networks are prone to missing results that work, but are functional.

There was an early experiment in hardware evolution by Dr. Adrian Thompson with FPGAs that had to recognize two different frequency signals - the end-result had five out of thirty-seven logic gates that were completely disconnected from the whole thing, but taking them out made it stop working, and was working with the individual chips' nuances and non-binary signals.

You'd never get this kind of solution via a deliberately engineered system.

That was an amazing read. IIRC some of the logic that was used actually performed no apparent function but removing that also stopped the circuit from working, and swapping a supposedly identical piece of hardware in with the exact same programming also failed to work.

[Helgoland]

Doesn't sound like too great a solution then.

[forsaken1111]

Doesn't sound like too great a solution then.

The point of the exercise wasn't to find a great solution but to determine if a solution could be evolved without input just by successively culling the failures and allowing the 'most successful' to breed. It was an experiment..

[scrdest]

Genetic evolution took billions of years to evolve humans, human's neural networks took only 10,000 years after learning agriculture to conquer Earth.

The two approaches may perhaps be optimized to different goals.

For example, the human neural networks are prone to missing results that work, but are functional.

There was an early experiment in hardware evolution by Dr. Adrian Thompson with FPGAs that had to recognize two different frequency signals - the end-result had five out of thirty-seven logic gates that were completely disconnected from the whole thing, but taking them out made it stop working, and was working with the individual chips' nuances and non-binary signals.

You'd never get this kind of solution via a deliberately engineered system.

That was an amazing read. IIRC some of the logic that was used actually performed no apparent function but removing that also stopped the circuit from working, and swapping a supposedly identical piece of hardware in with the exact same programming also failed to work.

Yeah, the first one was the disconnected thing I mentioned. The second is also true, swapping the FPGAs for an identically wired one broke it.

Basically, the evolutionary algorithm broke out of the box and started using the imperfections in the manufacturing of the gates as features. That makes it not very reproducible - but bear in mind the whole circuit also was 37 logic gates compared to tens of thousands in non-evolved sound cards that normally do that job.

[Helgoland]

Doesn't sound like too great a solution then.

The point of the exercise wasn't to find a great solution but to determine if a solution could be evolved without input just by successively culling the failures and allowing the 'most successful' to breed. It was an experiment..

Well yeah. But it also shows that you have to be very careful about what inputs you give to an evolutionary algorithm, since it'll work with the inputs you actually gave it, and not with the inputs you intended to give.

Kinda like the free market went for 'Kill the Irish' as a solution to the potato shortage. Technically it works, but it's not one you want...

[Starver]

I think that the AI being unable to adapt "beyond the presumptions of the programmer" is a good thing. It makes bugfixing the problems in AI so much easier, not to mention it reduces the chances of bad unexpected stuff happening.

And you no longer have a significantly useful AI, you merely have a tuppeny-hapenny ElizaBot that has no intelligence and can only deal with input anticipated by the designer.  (My own first Eliza program was typed into the BBC microcomputer in the early '80s... Knowing how it all works takes most of the magic out of it.  Tell me more about your mother.)

And no, neural networks are very much not "mutable code". There's a very simple algorithm in their core that's literally just repeated multiplication and summation of a certain set of input numbers, with weights given by data, and then subsequent update of these weights based on the outputs. There could be some kind of algorithm at the tail that processes said outputs to produce actions based on these outputs, but the algorithm itself doesn't change, either.

You're approaching NNs from a different angle to me, it seems.  To me, a NN node is defined as a logic gate (of a non-boolean nature, usually) programmed to monatomcally convert various linked input values/potentials into a single value/potential sent on to zero or more other nodes. This configuration can be defined as data, but then so would the string "if (pop(A) AND pop(B) and NOT(pop(C)) then push(D,TRUE)", even though it is obviously (pseudo)code when push comes to pop shove.  If the container-code that oversees the NN (in hardware or simulation/emulation) is modifying the behaviour of how the (real/virtual) decisions are made (not just which values are decided, whether the operands are immediate/direct/indirect/doubly-indirect/etc 'data', but the mix and relationships of the operators themselves) based upon some judgement of how well the tested input is converted to a desired output then it starts to look like it deserves the affectation of 'self-modifying code' to me.

Or, as a corollary, the Dwarf Fortress executable is obviously merely Data, as was its source 'code', as was the compiler 'executable' or its source.  As is command.com/whatever.  As is any prior bootloader.  As is the entire contents of the BIOS/UEFI. As are the microcode 'instructions' governing the operation of the chip.  The line can have a fuzzy and arbitrary location, depending on the phase of the moon and (possibly) the context of the examination.

AFAIK all genetic algorithm stuff hasn't gone beyond the labs.

Not sure if you mean CS labs, but have a look at something like this..?

And, while we're at it, human intelligence doesn't seem to work like genetic algorithms do, which further raises the question as to the actual applicability of this "genetic" stuff to something it wasn't actually designed for, and which has, in fact, shown some extremely poor performance in nature, compared to neural networks:

You (or someone else) originally equated genetic algorithms to AI.  Like NAND gates, it might be a useful massed-component of a full AI system, but a genetic algorithm wouldn't really be expected to be the entire AI.

Genetic evolution took billions of years to evolve humans, human's neural networks took only 10,000 years after learning agriculture to conquer Earth.

Anthropcentric, much? Neural networks exist in leaches, and even lowlier creatures. It's not even that we've developed intelligence, because octopuses, merecats, crows, cuttlefish and many other creatures (including our close ape cousins, of course) have intelligence of various kinds (social, tool-using, communicative...) and for some of these it may be that merely the lack, in parallel evolution to that of the mind, of suitable physiology (hands for tool-use, larynx for communication, etc) stops them developing their extelligence to the human level.

And our neural network (going by brain-mass) was developing far prior to agriculture, during the particular subset of billions of years of (unguided!) evolution that Homo took to get to the Sapiens (and Neanderthalis) stage.  It's not even as if Google's NNs, etc, are anything like a mammalian brain in structure or paradigm, even 'virtually'.

[Frumple]

Also it's silly questionable that we've conquered earth. Most of it we can still barely even touch, and we're significantly outmassed by a number of other things, to say nothing of how much our continued survival is dependent on things utterly outside our control. Our dominance of the biosphere is a delusion the bacteria in our brain deign to let us keep

[forsaken1111]

There is no part of the surface we couldn't destroy. That has to count for something right?

[Frumple]

Can we, though? Last I checked even at the peak of our destructive capability -- which we're not really at anymore -- we couldn't really manage that. Destroy human civilization, sure, wreck huge chunks of the biosphere, definitely, but destroy anything on the surface? Is shit out there that takes more than a sustained nuclear bombardment to get rid of. Honestly, our best bet is probably what we're doing environment wise, and even the worst of that is unlikely to surpass previous mass extinction events.

We're pretty damn good, but we're not that far, yet. We've still got a ways to go before we can even really top a sustained wide-scale algae bloom, and when you're being outperformed by pond scum, you don't get to claim superiority

[Criptfeind]

I mean, we'll never be able to call ourselves the masters of the earth in the very literal terms of the ball of rock whizzing around the sun, we'll never control that very much (although our dams are making surprisingly good try from last I heard) but I think conquered is a fair term. Sure, not the geology, but who gives a fuck about that compared to life? Not life I bet. And the life we've conquered pretty well. Sure, ants and other things might outmass us. But we certainly do hold their lives in our hands far far more then the other way around. Even if that's just because of a lack of brainpower on their side.

[TheBiggerFish]

"Never" is a hard thing to prove.

[Criptfeind]

True, but eyyyyyy. I'll be dead by then if ever so what the fuck do I care?

[Shadowlord]

"life we've conquered pretty well" - Criptfeind

Zika's knocking. It wants to know if you were planning on having children any time soon.

[Criptfeind]

Who's the bigger existential risk to who right now? Zika to humans? Or humans to Zika?

Edit: Well, admittedly I doubt we're going to wipe it out totally, but still. It seems far more likely that we wipe it out then it wipes us out.