Slashdot Mirror
Mutating Animations
Weird_one writes "Discover magazine's current issue has an intriguing article involving using genetic algorithims to evolve an animation of a walking individual."
← Back to Stories (view on slashdot.org)
← Back to Stories (view on slashdot.org)
When CPU's will become fast enough to use this level of learning on the fly, it will be great for gamers. Maybe the enemies don't have to learn walking, but learning strategy is a different thing. If they learn strategy by themselves and not by pre-programmed AI, I bet they will be more creative and a tougher opponent.
But I think I'll still have to wait like 20 years for that.
Not quite as slick but a lot more amusing.
Genetic algorithms must be stopped, and NOW
Who knows how soon it will be before these things gain the ability to work in the real world. It won't be long I tell you, before you look around and the entire PLANET will be full of these devilish unnatural creatures, all based on GENETICS.
... The genetic algorithm doesn't make the computer self-aware in a HAL 9000 kind of way...
Phew! That was a close one.
But I think I'll still have to wait like 20 years for that.
Not if you listen to Steve Jobs in senile old age...
"This 2.0 GHz G6 runs at 1000 times the performance of an 8.9 GHz Pentium X!"
Horse's mouth on the Topic
This sort of reminds me of golem@home....that thing never ceases to entertain me....all those cute little blocks moving around! What a fun screensaver....oh yeah...plus it has some scientific purposes too.
Gussy it up all you want, Trebek... But can the stick figures fight? http://www.cutthroatsd.com/
Hail thee, robot masters!
Evolution is a fraud made up by the godless devil-worshippin' computer scientists! Only God has the power of algorithm creation! The Bible clearly states in John 24:5 that God is the creator of the binary search, the hash table, the half-adder, the for loop, and matrix multiplication! You will all burn in Hell!
I don't know, it sounds really cool and all, but in my experience, anything involving Genetic Algorithms consists of more hype than results. I mean, say you want to actually use this system to make an animation of, say, a guy waving 'hello'? You would have to write a fitness function that gives more points for animations that look more like they are waving hello, then run the simulation, probably get weird results, and then go back and modify the fitness function till you get something that looks decent. How would this be any easier than doing keyframed animation with inverse kinematics?
& I wish I knew the password to your heart . . . &
Lunix8.
Anyone seen T3 yet?
Yes.... now they can finally make better 3D CG porn now that they can simulate and even teach computer how to have sex in better ways and different positions. Hey, isn't the whole point of "EVOLUTION" to "REPRODUCE" more offsprings??
.. animations don't mutate, its the program that mutates and represents its new self with animation.
How does the law apply to 'discoveries' versus 'inventions'?
Don't go to a brothel if you want to buy broth
The law doesn't see 'discoveries' or 'inventions,' it sees 'patents' and '$$$$$$$.'
no, you have to wait for it to be open-sourced for that.
When watching the video, I was rather disappointed when the 20th Generation figure at the end didn't trip and fall off the edge of the grid.
The other day I stumbled upon what could quite possibly be the coolest Java applet ever. Once you start the applet, you assemble "bioblocs," which are 3D creatures assembled from connected blocks. Once you've assembled your creature, you can have it use genetic algorithms to try to learn how to most effectively walk, run, jump, and turn around using the blocks you've given it. I assembled a snake-like creature the other day, and was intrigued to see that it evolved a walking movement very similar to that of a sidewinder's.
In addition to assembling your own creatures, you can also load creatures that others have previously assembled, as well as enter your creatures into contests. A lot of the previously assembled creatures are -very- impressive, with movements quite similar to those evolved in nature.
For those of you interested in a small open source project that deals with genetic algorithms, using Artificial Neural Networks, check out this sourceforge project:
http://sourceforge.net/projects/annevolve/
Dan
then will we get smarter OSs that learn to blue-screen all by themselves?
h-t-t-p-colon-slash-slash-slash-dot-dot-org
What needs to be done to make the GA work is to develop a solution space representatin in which each parameter can be varied independently of the others. In this case:
The character's body plan involved 700 distinct parameters that needed to be optimized to teach it how to walk like a human. .
So its not like the computer learnt to walk by itself. There's a lot of hard work involved before you can even start the GA. Congrats to Reil.
<shameless plug> On a slightly related note, I'm about to start implementing a GA to develop a killer AI for gtkboard . If you are interested in coding a GA, you are welcome to join :) (Of course it won't be anywhere as complex as the one in the article, but still lots of fun.)
I just got finished reading this book, and had to chuckle at seeing this article. The book is about a group of nanomachines given agent based programming called PRED/PREY which uses something like the genetic programming spoken of in the article. Of course things go awry in there somewhere, but it is an interesting, and moderately technical fiction on this subject.
Lunix10
While this isn't technically a GA approach, it does provide simialr results in real-time.
Check out his cool applet.
was it to post a story at this time of night? I mean, I'm at the risk of sounding US-centric, but this is the time of night when the trolls come out; and I guess they're too stupid to realize they missed the full moon.
You know what I always found interesting. It's like these systems of thinking create newer systems of thinking. Evolution created Neural networks, and eventually created neural networks that can think and create things much faster then evolution (the human mind)
Then the human mind goes and creates digital computers, which again can do things the Neural network can't (and vise versa).
Anyway, just thought it was intresting.
autopr0n is like, down and stuff.
An NP complete problem is one that takes non-polynomial time to find the optimal answer, but can be verified in polynomial time. A genetic algorithm is similar, you need to have a fast fitness algorithm, or an operator who does the selection for you. If neither of those things are practical, then you probably shouldn't use a GA.
On the other hand, there are a lot of things that you can use GAs for.
autopr0n is like, down and stuff.
Here is another movie (mpeg, 1.5 MB) demonstrating a set of legs learning to walk over time.
Reading the article, I was strongly impressed with what a good, ground-level introduction to the concept of "what is genetic programming". I think that showing the science applied to a seemingly simple, common concept (walking, and specifically animating virtual walking) really helps make the big concept here easier to understand.
Good article.
Heres the link to what they were talking about in the article. Walker Evolution
This next one shows off a lot more of what they can do. Mainly they abuse their models.
Natural Motion Show Real (14.5M Divx)
I love the tennis ball in the crotch clip. Insert bob saget joke here.
When I read the article, it immediatly made me remember the Boids which are a computer model of coordinated animal motion such as bird flocks and fish schools, first introduced by Craig Reynolds. Those where an example of emergent behaviour, where a bunch of independent moving things start moving in a coordinated way thanks to some "local guidelines" controlling their behaviour.
So, if every thing (boid) is telled to steer to avoid crowding local flockmates, steer towards the average heading of local flockmates and steer to move toward the average position of local flockmates, they start to move as a flock (!).
This approach of obtaining a more developed behaviour in an automatic (more accurately in an "emergent" way), is a lot related to genetic algorithms (GA) evolving an animation model, 'cos is exactly the opposite approach: In the first one the designer must specify the underlying mechanisms that permits the animation, while in the latter the designer must specify the result that is desired.
What I found more appealing of GA's approach is that the system can outperform the initial specifications, as is noted by a lot of papers in ALife. Some have developed an artificial world (in the paper linked above is named "Geb") where individuals can develope a (eventually) coordinated behaviour to survive (the fitnness function is an implicit
"survive function").
What would be cool is to use GA in a pre-determined way to evolve (in a explcit way) the basic behaviour that construct the coordinated mass beahaviours (like boids' flocking).
--krahd
mod me up, scottie!
mod me up scottie!
Karl Sims has also done a lot of work with evolutionary graphics and animations.
Check out his web site here especially the section on Evolved Virtual Creatures.
This freeware program from Jeffrey Ventrella is an open-ended version of this. Small wormlike creatures evolve to find the most efficient, fastest method of locomotion through liquid. You can change various parameters to make it easier or harder for the little swimmers.
DarwinBots makes use of true genetic algorithms for propulsion, attack, feeding, social behavior, and evolution of multicellularity. I like Darwin Pond better, personally, because it's more stable and DarwinBots doesn't have the "cuteness" factor.
Because these figures are engaging in human-type motion in a reasonably believable 3D environment, I can understand how it's important- however, it isn't truly revolutionary in nature. It's just another step in the evolution (appropriate, ne?) of genetic algorithms.
http://www.sodaplay.com/constructor/player.htm I found this link quite interesting to play with. Nothing to do with AI, but rather simulation of organic motion. Quite lifelike and it's fun to play with all the variables.
In case they get /.ed
naturalmotion.torrent
I found this link quite interesting to play with. Nothing to do with AI, but rather simulation of organic motion. Quite lifelike and it's fun to play with all the variables.
"genetic algorithms are increasingly being harnessed for real-world tasks such as designing more efficient refrigerators"
Wow. Walking refrigerators.
Lately, kind sir, I have been quite perturbed by certain events that have been proliferating in our society. Was it not so long ago, that in more civilized times, children respected and obeyed their parents, under the threat of a firm thrashing if their impudence and audacity got out of hand? But oh, kind father, the trials that parents today must suffer! Not just the other day, whist I was dining upon a fresh garden salad, my daughter, of not even 6 years old, insisted upon uprooting most unrest in requesting I purchase for her a milky-way bar! I quickly remarked to the impudent creature that one of our many servants would be more than willing to carriage her to the local general store; but no! she insisted that I -personally- drive the buggy to make the purchase! Oh wise man of God, what is a poor woman to do in these hard times! Before you can open your Moses-lovin' mouth Pastor, I have proposed a final solution to the problem of "youthful indiscretion"- Prison Labor!
Before you bring up cries of protest from your liberalism-saturated mind, hear me out! Our disrespectful children will learn the true meaning of honor and sacrifice while they're hard at work pounding license plates and assembling adding machines! Honestly, what better way is there to whip our children into shape? Scare them with threats of the boogey-man? Psh-haw! Just look at the wondrous effects prison labor had on the Dell kid! Not only will prison labor harden our children into obedient automatons, it will show them the reality they will have to face if they follow their current paths and become criminals!
Thank you for your attention kind Minister, and God-Bless!
Here's an evolution software for MacOS X (and a nice walker screensaver too!)
http://www.spiderland.org/breve/
"We got some creatures that didn't walk at all but had these very strange ways of moving forward: crawling or doing somersaults."
#include beer.h
Im dreaming ofa big bndwdth, That can resist the
In Soviet Russia the algorythms walk on you!
Im dreaming ofa big bndwdth, That can resist the
Arrrrggghhhh! Bill Gates's borg picture is changing to a penguin..
Imagine a beowulf cluster of these...
Dancing the Can-Can.
Im dreaming ofa big bndwdth, That can resist the
Greg! Long time, no see!
Comment removed based on user account deletion
Perhaps the way to develope real AI is only possible when the AI creation can request code to enable functions. Strange but perhaps open source is the route to self aware AI.
Flame me if you like but to lock down code might make real AI impossible.
It is possible to alow the bot to lock core code so that it will not self destruct, then if test routines cause problems the parent bot can decide to reject the code causing the problem.
An Ai bot that can program child processes itself based on sample test code might become possible, if we can teach bots to write code! Isaac Asimov and his rules of Robotics are starting to become very important indeed, his vision was as acute as that of Jules Vern.
OH THE SHAME I fell off the wagon and use sigs again!
I kept finding my programs in compromising positions in various parts of my hard drive. :-)
in my life God comes first.... but Linux is pretty high after that
Francis Smit
I think this is oversimplified. The number of generations necessary to find an acceptably good solution depends on many factors, most importantly population size and problem complexity (of course).
My experience with genetic algorithms is that with a reasonable initial population, the majority of progress occurs withing the first few generations. Were you refering to individual fitness evaluations instead of generations? Even so, given a reasonably optimized initial population, and a quick method for approximating fitness (or at least weeding out poor candidates), I would expect useful results could be had in a handful generations with a small population size (ten or so), so maybe a hundred or two hundred evaluations of individuals.
If you are referring to genetic programming, rather straightforward genetic algorithms, I am not sure how many iterations that would take, I haven't any practical experience with them.
In terms of games adjusting to playing style, I would expect other types of learning algorithms to be more useful, though.
sodaplay always looks to me just like xspringies - an x windows spring/mass simulation thats been around for quite a while. Its quite a fun thing to play with - you can take one of the defined models and change gravity, the strength of the springs and so on and see how it works.
It doesn't evolve moving critters, but one of the included examples evolves 3d plants that compete for sunlight (kind of, sort of).
Another of the examples included allows the user to evolve midi files - with seriously odd results. Things may get odder though, I'm currently trying to figure out how to decompile midi files into source grammars then do crossover and mutation on them. Imagine Mozart crossed with Metallica.... Beethoven with the Brittany, or... I'd better not say, likely to get attacked.
Part of DALi's technology from nearly three years ago approached the problem of creating lifelike ALife entities in much the same fashion.
See http://www.dalilab.com/ for more information and a technology demo.
Joseph R. Kiniry
http://kind.ucd.ie/~kiniry/
Lecturer
UCD School of Computer Science and Informatics
My mac has a screen saver that does that. Whoop-de-friggin do. (the screen saver is cool. this posting masquerading as news is not.)
;). Get over it.
This would hae been news back in the 1900s
blog
On my website I implemented a genetic algorithm to choose the colorscheme. The number of pages people view determines the amount on influence on the general color scheme.
http://douweosinga.com/projects/colorscheme describes it in more detail.
I just RTFA'd and it's not really an example of the kinds of animations the article talks about. In the article the point of mutations was to find working solutions to problems but in Tom Thumb the mutations are there just for art's sake. And they are not even genetically based :-)
Interesting stuff nevertheless.
The field of machine learning consists of probably at least some 1000 researchers worldwide. Genetic Algorithms in the way they are usually used are an algorithm for optimization.
The problem of optimizing: You have a set of parameters p_i. You have a fitness/ energy or objective function F that somehow measures how good you are doing. The algorithm is supposed to yield some p_i that lead to optimal performance, that is maximal F.
What is a good algorithm? Whereas some years ago people would write sentences like "my algorithm is better than your algorithm" we now know that without prior knowledge about the function to be optimized all optimization algorithms are equally good. So today you can only say ... my algorithm works better for this and that type of data because it incorporates this or that knowledge about the problem encountered.
Algorithms used Depending on what you know about the problem set you can then build various algorithms. The following are among the most common algorithms for optimization: Methods based on gradients (i.e. vanilla, conjugate gradients), Methods based on random search and genetic Methods.
Why this is a good example for using genetic algorithms Genetic algorithms completely ignore the gradient information. In the case of walking the gradient of the fitness function may be difficult to define. That is why this is a classical example of using genetic algorithms.
Why genetic algorithms are absolutely hopeless for more interesting problems Genetic algorithms do not obtain a lot of information. In Particular for example David MacKay shows that the number of bits per generation is very low (1 bit for asexual, sqrt(size(genome)) for sexual systems). This means that the information acquired per generation is very low and that to obtain human like abilities it would take forever.
For interesting problems other optimization methods must be used that use information from the environment in a far more efficient way. Without learning I guess there can not be human like performance.
Googlefight "Slashdot Troll" against "BSD is dying" 303:229. BSD thus cant die.
When I read this article, my mind immediately conjured up sodaconstructor. With this applet, you create a bunch of "tendons" and/or "muscles" (line segments) connected together. You then adjust the function that controls the cycle of tension on each segment. The result is that you can make "creatures" that walk.
The thing that triggered this memory was the talk of "700 independent parameters". I pictured each muscle in this virtual walking body to be much like the line segments in sodaconstructor. The difference is that instead of a human thinking about how to adjust each one, random mutation adjusted them and evolution selected them.
Animators then went crazy with the idea and brought Luxo to life (through traditional keyframing).
[
The practical side of me says it would never fit into the usual slot they are stuffed into by kitchen designers, but I like it anyway.
Proof positive that with enough intelligent design and a keen eye for the result you're aiming towards, you can have a carefully manipulated, narrowly defined creation take on properties that look just like they evolved, if you stringently ignore the fact that they were intelligently designed, keenly aimed, narrowly defined, and heck, made in your own image. Now if they could only get the stick figure to say, "I am fearfully and wonderfully made."
Windows XP SP2 told me to install third-party software that prevents viruses and protects stability... I chose Ubuntu
Shouldn't the same development process be possible to use for robot controller SW? You will of course have to change the physiological input parameters (the robot you are constructing will most likely NOT have the same muscles as a human body), but the process should be the same, and the resulting controlling algoritm would be better at controlling the robot walk (move) than a human-constructed program.
SIG: TAKE OFF EVERY 'CAPTAIN'!!
I for one welcome our new genetic algorithm masters!
Genetic algorithms work by minimizing the amount of searching needed in a search space by "evolving" candidate solutions and only evolving new ones from the best of the old ones. A candidate solution is evaluated against a fitness (of objective) function that assigns a fitness to a candidate solution.
Don't get to excited about the walking man - the difficulty and also art in Genetic Algorithms is finding a way to represent a candidate solution. The walking man isn't difficult to represent. To make it simple, pretend that the representation is like, work out a way to order the numbers 1..10 - where 1 == man crawling and 10 == man walking and the rest of the numbers in between are ordered to represent a certain posture. The genetic algorithm then searches through all the combinations and permutations of the numbers 1..10 until they are ordered - btw, instead of drawing numbers let's associate a number with a posture.
Now with this problem - think of a pool of numbers, each number associated with a posture and the Genetic Algorithm searches through the pool (of 100) until it finds the numbers 1..10 in order all standing next to each other.
---
Analytic & algebraic topology of locally Euclidean meterization of infinitely differentiable Riemmanian manifold
i think you mean
one crowd simulator to rule them all
Free as in mason.
The demos mostly show the figures being hit, blasted, or shot. Maybe that's to appeal to game makers, but it suggests that the figures still have a rather limited repertoire. I'd like to see more gymnastics and other complex body movement, not just the physics model of a jointed body crumpling.
you should really check out framsticks.
you can even see the current generation walk or crawl in 3d.
one of the coolest programs ever
some screenshots here
Are you talking about the gtkboard development, or some other project you got running?
It sounds interesting...
My other
"The idea is called a genetic algorithm. It creates a random population of potential solutions, then tests each one for success, ..." The author also calls it "fitness function." Where in the world would such a thing be found in nature: The idea that there is some goal of walking or having wings or having skin instead of scales or wings instead of fins or limbs.
This program, like any other "successful" program is not successful unless some outside force (in this case a human) tells it when it will be successful. It is nothing less than preposterous to state that there are "successful" genes in nature (see end of second paragraph). How would genes be known, particularly in the case of the "evolution" of walking, to be successful unless some outside force had designed it to so that it would
So, my conclussion is that you know nothing of programming, don't care about programming, are willing ignorant of the logic expoused above, or are set in your religion of evolution and when a straw comes along to grasp at you take it, even when it makes you look like a hater of reason.
The opening quote from the last paragraph reads:
But the one quoted should have instead said:
I first learned about genetic algorithms back when I was working to break the Poe Cipher (I did break it, but wasn't the first, I think my submission was 6th - I was using Perl and the winner was using C - if that matters).
I was fascinated by them and have always read up all that I could about them.
Then moved on to neural networks, and then thought of genetic programming (I'm certainly not the first of course to think of that, and I'm not claiming I am).
These are great for getting through non-linear solutions faster than with linear attempts at the problem space. The main issue is that you tend to find local max/min (in theory which you are shooting for depends on what you are using it to find - I'm pretty sure everything I've ever used it for was looking for maxes) and you want to ideally find the global max/min - the thinking being that for the given problem space.
In many cases, and this walk cycle sounds like it is perhaps one of them, a "pretty good" local max/min is sufficient and you don't in fact need THE global max/min.
I have thought of ways of using them for voice recognition, face recognition, stock market prediciton, etc etc - again, I'm not the first person to think of this - it is likely just a logical progression as you think of areas with huge problem surfaces and you want a non-linear solution.
In terms of game UI, or at least games in the sense of what we play on our computers, FPS and the like, they aren't used all that often. They require a pretty large lifetime in terms of how they learn (many repetitions and attempts).
What is usually more prevalent in game UI is Bayesian learning via hidden Markov Matricies. Those are imprefect as well, but give the illusion of learning fairly well. Those can learn slightly faster, and can also be pre-taught when put into the game (trained on a wide range of users) and then learn more to the specifics of their new owner once they play.
I have a lot of code now for stock market prediciton because I find that to be the most interesting field for using this. I am actually in the process of starting up a company using it - I need to finish the UI for the end users, and I need to work out the legal side of it and where the company will be loccated in terms of the legal side for taxes.
In terms of predictive ability, neural nets trend towards making more predicitons, but some of those will be wrong. Genetic algorithms will make fewer predicitons because they will "try" harder to be right instead of just making a prediciton. "Try" being relative here because the bulk of that is in how they are programmed.
Genetic programming is intersting since you don't really write the code for the end problem, but instead define what the problem is, and then you write code that writes code to solve that problem.
The downside of that is that it doesn't make fast and efficient code, it usually makes code with lots of conditions and branches.
In the end, you are usually going to need to go over the code that it writes and then rewrite it yourself so that it does the same thing, but more efficiently - using the genetic programmed code as the guideline.
(I'm 99% sure that in the recent article about GridWars and how the 2nd place guy used a "genetic algorithm" to determine his code - I think they were actually referring to genetic programming, which is slightly different - and judging by the fact that his code was very thick, and the fact that was likely why it lost in the end - too slow - also makes me think that was the case)
Fun stuff - I sure hope my company idea takes off so that I can just work on that and be done with the whole IT thing that is essentially really boring compared to all of this.
There are some odd things afoot now, in the Villa Straylight.
Looking at their demos, I can see where what we now think as realistic console sports games could be greatly improved by the use of this software.
They've got a couple of clips involving catching a football, getting hit with something, etc. It's so lifelike it's scary.
I'm very curious what the CPU requirements would be of having 22 of these creatures playing within the rules of football at once.
Who knows, NCAA Football 2006 on the PS3 may be a "real" reality.
I'm sorry I'm posting this off-topic, but I can't seem to find any "dedicated" forums. The only ones I see, are the ones that belong to the news stories. I wish to ask a question to those Slashdotters who are programmers, where would I post such a question?
Thanks for any help,
Mad Hatter
The software made 20 copies of their neural networks, introduced subtle mutations in each of them, added 80 new participants with randomly wired networks, and started the next generation walking.
That isn't a genetic algorithm, if there was no crossover then its Monte Carlo. I guess it's just the journalist making a mistake. This is a popular misconseption that evolution occurs only through mutation. I guess it's exciting to think about large evolutionary jumps caused by mutation - like in X-men or something - than the slow process of gene recombination.
Tom.
--Wow, that does sound interesting. Anyone care to explain the concept in maybe a paragraph?
q a.aspm agazine s.asp
/me puts on flame-retardant suit ]
--On the other side: Whenever I see stuff like this in an article, it really tweaks me:
> Watching the time-lapse video clips, one can't help but marvel how this virtual evolution is roughly analogous to the real-world evolution of our ancestors millions of years ago when they first began to walk upright across the savannas of Africa.
--Blegh, what a bunch of hooey. Um, just a thought to all you Slashdot readers out there: If you haven't yet done so, DON'T accept the "theory of evolution" blindly - INVESTIGATE IT. Thoroughly. Having done so myself, and basing my decision on evidence seen with my own eyes, I can confidently point to the Bible and the book of Genesis and say "Yup, that makes a lot more sense than me being descended from some kind of monkey."
--I suggest you start here:
http://www.answersingenesis.org/home/area/
http://www.answersingenesis.org/Home/Area/
[
.
== WolfriderV6 == I'm willing to admit that *I just might* be wrong... Are you??
Running, though, is harder. Steady-state running is reasonably well understood, but running on rough terrain remains hard. To control running well, you need predictive techniques - look-ahead, two-point boundary value solvers, and model-based control. This is where the insect brain leaves off and the lizard brain starts, and may be the beginnings of low-level AI.
Patrick: "Itsa robotic Sponge Bob with long legs. Run for the coral!"
Table-ized A.I.
I recall seeing a video some time back where someone was trying to make some swimmers and walkers from blocks tied together with a simulated spine. The swimmers were great - they eventually evolved into something resembling fish.
The walkers, on the other hand, took advantage of an error in the scoring system. Since they were graded on the distance that they moved, most of the walkers evolved into tall and skinny objects, and simply fell down. The taller they were, the higher the score. Oooops.
But the real issue is that you don't have control over the GA algorithm. You want to be able to specify a particular sort of walk - staggering zombie, happy double bounce. GA won't give you that.
Heck, even Poser gives you that option.
It is kind of peculiar that all of their demos have a rather quick and abrupt hit/fall/tie/don't move much animation sequence. At first it is amusing but it appears all the animations are like that. Thought I'd point that out.
http://www.critticall.com
Dammit, my cat just morphed into an agent again...
A rolling stone is worth two in the bush!
If you attached a 3d engine onto CYC, you can trail and error, learn how to use limbs you attach onto a robot. Eventually its using the best result as it learns to grasp... Then when it judges weight/shape/density/wind, and throws, it can learn how to best hit a target.
I'm interested to see which AI is seen first. We'll probably have both versions of AI down the line though. I wonder if there are any more AI possibilities.
God spoke to me
If you're a genetic algorithms fan, and want to participate, take a look at Darwinian Poetry.
Actually, I was trying to be Insightful, not Funny.
We tried to use them in my last company (which fucked up). Promising results at first, but u can't read the code and improving the ga's is damn hard. Only feedback is the behaviour of generated code. And no one is really sure what it is doing...
While this is pretty cool, it's nothing like "real" evolution. They started out with a humanoid figure and gave it a bunch of parameters and asked it to walk.
What they didn't do was say things like:
- the figure has to live on a planet with a certain amount of gravity
- food may or may not be plentiful
- temperature can change
- must be durable over many years and able to handle many terrains
- give no shape or composition to start with
- and so on...
Sorry, these models are just cool toys.
Think Terminator.
nuff said.
I got slashdotted indeed. However, your torrent has 0 seeders.. what gives?