Slashdot Mirror
Swiss Experimenter Breeds Swarm Intelligence
destinyland writes "Researchers simulated evolution with multiple generations of food-seeking robots in a new study of artificial swarm intelligence. 'Under some conditions, sophisticated communication evolved,' says one researcher. And in a more recent study, the swarms of bots didn't just evolve cooperative strategies — they also evolved the ability to deceive. ('Forget zombies,' joked one commenter. 'This is the real threat.') 'The study of artificial swarm intelligence provides insight into the nature of intelligence in general, and offers an interesting perspective on the nature of Darwinian selection, competition, and cooperation.' And there's also some cool video of the bots in action."
Of all the Nations, I would never have thought it would be the Swiss who would start the robot apocalypse. I had Germany in my betting pull...
"Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
First XKCD points out the obvious weapons end of things, now this guy announces how the brains have already been developed.
Behold, this dreamer cometh. Come now, and let us slay him... and we shall see what will become of his dreams.
To counteract his theories about swarm-intelligence, I sent the researcher link to 4chan.
There are no atheists when recovering from tape backup.
In other news, an experiment by SourceForge, using it's meatspace zombienet "Slashdot" proved that even Google-owned YouTube can be brought to it's knees by enough people trying to watch the same video at the same time.
"Prey" is a pretty good scifi novel about this. It follows the tired cautionary-tale forumla, but like all of Crichton's novels has (some) basis in real research.
Caffeine is my anti-drug!
Duranin - A NWN2 Roleplaying Persistent World
"Crabs Take Over the Island" by Anatoly Dnieprov is somewhat based on the same idea, not in that swarm scale, but scary anyway.
they also evolved the ability to deceive.
Obviously, once you've proved the entity has the ability to deceive, you must distrust any further results.
Do I understand this correctly? On top of superhuman strength and intelligence, we're now making steps toward robot evolution? When robots rule the world, do you think they'll debate whether or not they actually evolved from primitive PCs?
"You fool! We were created in our present form by the great nerd in the sky! Shun the non-believer!"
conspicuously absent is any explanation of what is meant by "learned" in this context or how the algorithms "evolved"
Um, it's in the first couple paragraphs of the article. You did read that, yes?
in this post: http://hardware.slashdot.org/article.pl?sid=09/08/19/185259
I did. Did you understand the meaning behind the paragraphs you cite?
I am confused as to how it was possible to understand the claims it made. Robots don't have genomes and don't eat food. Their "genomes" cannot be recombined.
Robots have code and programmers. What does a random change mean in this context? Do they use faulty dram or mess with the voltage?
Actual robots with flashing lights have a way better chance at going viral on YouTube.
If libertarians are so opposed to effective government, why don't they all move to Somalia?
Of course he was only joking! He knows just as well as we all do, that the outbreak of a Zombie apocalypse is way more likely than his swarm bots eating our brains. Because the robots won't reproduce exponentially by eating your brains, they will have to rely on the superior robotics skills of the zombies to survive.
From TFA: "First simulated in software before using actual bots, five hundred generations were evolved this way with different selective pressures by roboticists and biologists at the Ecole Polytechnique Fédérale de Lausanne in Switzerland in 2007."
So yes, that's exactly what they did.
Also, I'm sure this is at least a rehash of a previous /. article, because I remember discussing the deceptive behavior with the light-flashing. It's still interesting.
The enemies of Democracy are
Well, I did not read the article, but maybe they're talking about genetic algorithms?
factor 966971: 966971
Don't worry, I didn't read the article either.
I did however do a text search and came across this line: "First simulated in software before using actual bots"
We have not even realized swarm stupidity yet, how can they claim swarm intelligence?
Hope is the currency of fools
Real hardware can hold more states than a purely digital system.
I remember reading a paper (can't find it now though - darn it) about a guy who was doing neural net research with Xilinx chips. Same idea. Whenever an algorithm would do well he'd break it into "genomes" and pair them off with other successful programs.
The board was a bank of Xilinx chips, the genomes were the programming files (basically 1s and 0s fed into the configuration matrix), and the goal was to get the thing to turn on and off when you would speak "on" and "off" into a microphone.
It eventually started working. More interesting than that is what happened when he loaded the program into another board. It didn't work.
It turns out the algorithm had evolved to take advantage of the analog properties of the specific chips in that particular board. The algorithm didn't see the board as a digital thing. It saw it as a collection of opamps, amplifiers, and other analog parts. Move the program to a board that is identical digitally, and it failed because the chips weren't analog exact. You wouldn't have seen that behavior in a purely digital simulation.
Weaselmancer
rediculous.
Just with the limited human intelligence, limited resources and limited ability the researchers are able to create great levels of cooperation on mindless robots without any free will. Makes me wonder, if we are designed, as many Intelligent Design advocates claim we are, was the designer "intelligent"? With infinite wisdom and omnipotence and infinite resources, the Designer (or Designers) should have been able to create much more cooperative human beings. No wars. all peace. I wonder how they (the IDists) are able to square their ability ti "infer design" with the obvious "deficiencies of design".
sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
The "food" is just something that they're supposed to move towards. I have heard of similar (hobbyist) setups where it's actually a charging station so the "food" aspect is more literal, but all that's necessary is that something keeps score to see which bots found it (and should be used for the next round) and which ones didn't (and should be discarded).
The "genomes" are something like config files for their programming.
New bots got config files made from random (well, probably pseudorandom, but that's just as good in this context) sections taken out of the config files of earlier bots, probably with some small bits completely randomized.
(Note that "config file" here is based on the reporter calling it a set of parameters. I'd imagine it could be anything from a normal config file to a script in some appropriate high-level language.)
There's what seems like a decent overview of how these things work in general over here.
I did. Did you understand the meaning behind the paragraphs you cite?
I did! Whenever you hear about a robot/AI "evolving", you should immediately think Genetic Algorithms. Most frequently in association with Neural Networks as is the case here (mentioned lower in TFA).
I am confused as to how it was possible to understand the claims it made. Robots don't have genomes and don't eat food. Their "genomes" cannot be recombined. Robots have code and programmers. What does a random change mean in this context? Do they use faulty dram or mess with the voltage?
Robots have code. That code can be (is) represented as a series of bits. That series of 1s and 0s can be considered the "genome" of the robot. And can you randomly change bits, or recombine portions of bit patterns? Absolutely. When you have a "population" of such bit patterns which you test out, then take the best ones and copy them, randomly mutate them, and recombine them together, then test the new population and repeat, you have a Genetic Algorithm.
Now that's possible but time consuming to do with the actual instruction bytes of the AI. In the case of Neural Networks with Genetic Algorithms, the "genome" is actually just the organization of the neural net -- the connections and weights between the neurons.
The robots still have programmers, but the programmer is not directly writing instructions for the AI to follow. Instead, they're writting an interface between the robot's sensors and the neural network, the neural network code itself (not its organization), and the code that does the genome mutation/recombination. From there, the AIs "evolve" and "learn" on their own and arrive at often fascinating solutions to problems.
For example in this case, the programmers did not teach the robots how to deceive each other. That behavior emerged on its own from the genetic algorithm. So, there really isn't any hyperbole at all in the summary/TFA. Though it would be helpful if they at least mentioned genetic algorithms so skeptical people have something to google. :)
The enemies of Democracy are
Why even bother with robots? So it looks more real and tangible than just a computer simulation? Maybe, but other than that it's a waste of time and resources. Anything you could learn you could learn from a simulation of those robots, since this is entirely an algorithmic problem. I guess these guys just like to play with robots.
You just got troll'd!
it sounds like you are now accepting that the article is misleading.
You're agreeing that the terms are not what a normal reader would construe them to mean.
if the experiment wants to show anything, the methodology has to be more transparent so that we can know whether to consider its "genome" as really a genome or are something more banal.
if the semi-random is really just someone going through and changing parameters in a config file (or using a script to do it), then it's not really random at all.
here's a url that helps make sense of the difference: same site [wikipedia.org]
One question that intrigues me is just how human-readable the code produced by such genetic algorithms is. Some of the practical promise of this work is that it produces problem-solving code in ways very difficult from that of human programmers -- but how can such code be maintained by humans? It's a bit like making an engineer try to figure out how your lower intestine works.
Stargate story. Stargate world. Stargate creation. You can call it anything you want other than Stargate Universe. That show is TERRIBLE.
The only change I can believe in is what I find in my couch cushions.
it sounds like you are now accepting that the article is misleading.
You're agreeing that the terms are not what a normal reader would construe them to mean.
The terms are a (very good) metaphor, and the article is not at all misleading. I would have thought this would be obvious.
if the experiment wants to show anything, the methodology has to be more transparent so that we can know whether to consider its "genome" as really a genome or are something more banal.
The entire point of this sort of research is that the "genome" in the bots is analogous to, but far simpler than, a biological genome, and the means of selecting which "genomes" to generate the next "generation" from is analogous to how genomes are selected in biology (either "natural selection" like you find in nature or "artificial selection" like you get with farmed crops or dog breeding).
In what way is it not transparent?
if the semi-random is really just someone going through and changing parameters in a config file (or using a script to do it), then it's not really random at all.
Believe it or not, computers actually can generate effectively random numbers.
The terms are a (very good) metaphor, and the article is not at all misleading. I would have thought this would be obvious.
unless you're the author of the underlying study, I am unclear as to how you have knowledge of the methods and science behind what they are doing.
I would have that this would be obvious
The entire point of this sort of research is that the "genome" in the bots is analogous to, but far simpler than, a biological genome, and the means of selecting which "genomes" to generate the next "generation" from is analogous to how genomes are selected in biology (either "natural selection" like you find in nature or "artificial selection" like you get with farmed crops or dog breeding).
the entire failing is that it's not clear that the simplified model in any way duplicates the more complicated model.
oddly, when you simplify something, you often bludgeon the very thing that makes it what it is. What has made genetics so interesting is that the pathways of inheritance and gene expression are more complicated than each model we devise.
So without knowledge of the senses in which this is reflective of a "genome" to call it so is misleading.
In what way is it not transparent?
see above. The opacity is the validity of the comparison not the use of the comparison.
Believe it or not, computers actually can generate effectively random numbers.
Believe it or not, the article makes no mention of this and does not indicate how the randomization was effected.
oddly that failing is precisely what i questioned to begin with ... believe it or not.
in summary, while you have marshaled an interesting array of wikipedia articles, the original article in question remains a piece of hype-mongering.
it has in no way connected itself to any of what you have stated.
instead, it has merely used (or possibly abused) the terms of biology to describe what might otherwise be a rather boring high school science fair experiment.
With infinite wisdom and omnipotence and infinite resources, the Designer (or Designers) should have been able to create much more cooperative human beings. No wars. all peace.
Well, by Norse mythology, Odin, Vili, and Ve created the humans to fight in the final battle of Ragnarok, which wouldn't be much of a battle if humans just sit around all day and post to slashdot. The world is supposed to end in flames, perhaps Ragnarok will be started by a vi vs emacs flamewar on slashdot. Certainly the Norse mythology fits the human condition much more closely than the Christian mythology. Which would imply...
I wonder how they (the IDists) are able to square their ability ti "infer design" with the obvious "deficiencies of design".
If you really want to mess with the heads of IDers, ask them what they'd do if further research showed neither the Christians nor the scientists are correct, and it turns out they're worshiping the wrong gods.
"Science flies us to the moon. Religion flies us into buildings." - Victor Stenger
Somewhere out there is a darwin award for species behavior. Our award might be for inventing our own successor.
soooooo... Destiny vs. free will & self-determination?
I RTFA and think it's geeky cool just for the robots, but I wonder about how to apply this to real life. How could we use the algorithms to improve our router firewall, or kernel scheduling, or even better dynamic playlists on our favorite music players? Could we have our coffee makers figure out when we would ACTUALLY like our coffee being brewed?
I call it 'The Aristocrats'
Well, I can't speak for all "IDists", but based on my beliefs we are here to learn and progress: that is the whole point of our existence. Progression implies a lack of perfection, hence the wars, lack of cooperation, etc., that you suggest is evidence of a lack of intelligent design.
We are all intelligences in our own right, given the freedom to choose for ourselves and in so doing gain knowledge, experience and indeed greater intelligence. This freedom we are given means our actions can prove to be positive and conducive to progress or detrimental to ourselves or the human race as a whole.
It's commonly accepted that we learn by experience: we see evidence of that on a daily basis. Why does that suddenly seem ridiculous when it's suggested that that is what our Creator had in mind for us?
"Evolution of Communication in Perfect and Imperfect Worlds "
http://sunysb.edu/philosophy//faculty/pgrim/pgrim_publications.html
http://www.sunysb.edu/philosophy/faculty/pgrim/evolution.htm
"We extend previous work on cooperation to some related questions regarding the evolution of simple forms of communication. The evolution of cooperation within the iterated Prisoner's Dilemma has been shown to follow different patterns, with significantly different outcomes, depending on whether the features of the model are classically perfect or stochastically imperfect (Axelrod 1980a, 1980b, 1984, 1985; Axelrod and Hamilton, 1981; Nowak and Sigmund, 1990, 1992; Sigmund 1993). Our results here show that the same holds for communication. Within a simple model, the evolution of communication seems to require a stochastically imperfect world. "
A 21st century issue: the irony of technologies of abundance in the hands of those still thinking in terms of scarcity.
Same story more than a year ago: http://hardware.slashdot.org/hardware/08/01/19/0258214.shtml
/.? Really?
And offtopic: $&^@%! Taco, what's up with the popups that sneak past Firefox popup blocks? I've dutifully allowed advertising to continue, despite having that checkbox I could click to turn ads off for good behavior. Do I really need to turn on adblock and noscript for
Yes, you would, but you'd also take a hit to simulation throughput, I'm guessing a pretty significant one, too. I'm not sure you'd gain anything specifically more useful than you would in a pure digital approach without this kind of low level detail, either. More interesting to add something a bit more "macro" in the sense that it's a high level behavior / feature you can see and evaluate by simple observation.
My qualifications to guess? I'm the author of "Digital Soup", a system that uses genetic algorithms to drive robotic actors ("crits") in a world where simulated food gives them energy, they can trip over simulated rocks which takes energy from them, they can bump into each other -- similar to tripping on a rock -- they lose energy in the search for food, they can mate, breed, and so forth.
You have control over breeding selection criteria, in that they (the crits) can pick from other crits that are high performing, or one of them can be, or neither, or it can be random. You can also fiddle with how the genomes of the breeders mix. You can hand-write the genomes, or preload from saved before you start, or you can generate them randomly.
Once they're let go, performance is evaluated on a per-crit basis using a histogram for the currently living crits that evaluates their energy state. You have control over the size of the living space, the number of crits... and more. You can actually watch them run around, chase food and each other, avoid rocks, etc. Generation times can be exceedingly fast. Built-in hypertext docs/help. It is really a pretty cool program.
Also... if you write a genome yourself, one you think will do well, the result is very rarely what you expect. It's fascinating to mess with.
You can get the software for free here, but there is a pretty big catch for most people: It's Amiga software. I wrote all this over a decade ago. It probably would run fine on any decent Amiga emulation, though, as there's nothing "funny" about the code or the resources used.
I've fallen off your lawn, and I can't get up.
in summary, while you have marshaled an interesting array of wikipedia articles, the original article in question remains a piece of hype-mongering.
it has in no way connected itself to any of what you have stated.
instead, it has merely used (or possibly abused) the terms of biology to describe what might otherwise be a rather boring high school science fair experiment.
Oh, I see. You're not complaining about this specific article, you're trying to claim that that entire field is a crock.
Have a nice day.
According to the article they optimized the behavior by optimizing a computer simulation with a genetic algorithm. Says they ran 500 generation which is a very small number of iterations for a genetic algorithm. Then, after they had optimized the behavior, they put the control code into the robots and watched them go.
I have an even better question for ID'ers. What does THIS say about their so-called intelligent designer?: http://en.wikipedia.org/wiki/Penis_plant
Were we created by Beavis and Butthead? I can imagine the scene on Day 3 or thereabouts of the Creation:
[God] Huh-huhuhuh-huh-huh. Hey, Lucifer. Check this out, dude. *zap!* It's a schlong cactus. ...what's a schlong?
[Lucifer] Heh-m-heh-heh. Yeah, that's pretty cool, m-heheh. Schlong.
~Eien no Inori wo Sasagete~ Searching for my Hatsumi...
Ok, what did this study teach us that wasn't learned years ago in (for example) Boids (1987), Core War (1984), and Tierra (1991)? I mean, it's cool having little bots running around a tabletop and all, but I was simulating the same behaviors on my '286 back in the mid 90's.
unless you're the author of the underlying study, I am unclear as to how you have knowledge of the methods and science behind what they are doing.
Electron microscopes have been around for decades. So long, in fact, that you do NOT have to explain how an electron microscope works every single time you show a picture taken with an electron microscope. Instead, you publish an article and you say "figure three was taken with an electron microscope" and anybody unclear on the subject can go and read up on how that works.
In the exact same way genetic algorithms have been around for decades. And in the exact same way, you do not have to spell out the precise details of what you're doing every single time you're using one. It is entirely sufficient to say "we used a genetic algorithm to evolve a certain behaviour (like food-seeking or poison avoidance) and found the following interesting social strategies...".
If that isn't enough information for you, then it is up to you to dig up the peer-reviewed literature on the details. In the exact same way as it would be with an article about microchips that happens to show an electron microscope picture without precisely spelling out how electron microscopes work.
If you aren't going to do that, then it means you're lazy, not that the article is "misleading".
We're all born with nothing.
If you die in debt, you're ahead.
unless you're the author of the underlying study, I am unclear as to how you have knowledge of the methods and science behind what they are doing.
Electron microscopes have been around for decades. So long, in fact, that you do NOT have to explain how an electron microscope works every single time you show a picture taken with an electron microscope. Instead, you publish an article and you say "figure three was taken with an electron microscope" and anybody unclear on the subject can go and read up on how that works.
In the exact same way genetic algorithms have been around for decades. And in the exact same way, you do not have to spell out the precise details of what you're doing every single time you're using one. It is entirely sufficient to say "we used a genetic algorithm to evolve a certain behaviour (like food-seeking or poison avoidance) and found the following interesting social strategies...".
while i appreciate your attempt, it is unfortunately ill-adapted. The problem is that there's a fundamental dis-analogy between the two cases.
In the first case, "electron microscope" is a phrase that has only one usage and meaning. It does not have multiple possible understandings.
In the second case, this is apparently not so. "evolve", "food", and "genome" have a standard meaning which refer to a process in biology, sustenance for animals and plants, and the bearer of genetic material in the form of DNA/RNA and methylation.
the usage you are making of these terms is not this. If I want to use the term "Iron Condor" to refer to a mountain range near where I live, I should not go about publishing popular press articles as if I am referring to the same thing that others refer to.
as a second example, if I write a visual basic program and call it SQL, then publish an article about how I improved SQL 500%. I should really explain that I am not talking about the database language.
that's exactly what I am asking of the article.
If you aren't going to do that, then it means you're lazy, not that the article is "misleading".
I feel you're not putting your critical thinking cap on here. Your analogy was utterly disanalogous.
ummm...there's a difference between "Stargate Universe" and "Stargate universe".
One is the show (which has potential...but is not the same "stargate" like the others that have come and gone)
You assume that collective peace and smurfiness is the ultimate goal, and not individualistic peace/enlightenment/salvation/etc, which most religions tend to focus on.
There is a difference between VC (Viet Cong) and VC (Venture Capital) but someone scarred by Vietnam is going to have an entirely different plan in mind when someone says "Let's go look for VC"
As far as potential... That plot has holes you could fly a Goa'uld Mothership through! Even ignoring the whole video game garbage and that cheese like that was only ever part of intentionally cheese episodes of previous series...there are more logical inconsistencies than I can count. At first glance it wasn't terrible, but the more I thought about it, the more unbelievably stupid holes there were.
The only change I can believe in is what I find in my couch cushions.
I'm surprised they didn't use a Windows symbol instead of those skull and bones.
That apple looks like a familiar sticker one gets when buying a certain computer.
It slows down exponentially with time. No apocalypse there.
-- Programming with boost is like building a house with lego. It's a cool but I wouldn't want to live in it
A little product placement anyone? Kinda reminds me of those old films of white corpuscles attacking bacteria.
For justice, we must go to Don Corleone
My wife was watching the show I sat down for a couple minutes then promptly left when I saw one of the characters using a sharpened #2 pencil to write.
open source sub sim. I might start coding again for this. http://dangerdeep.sourceforge.net/contribute/