Artificial Life Forms Evolve Basic Memory, Strategy 206
Calopteryx notes a New Scientist piece on how digital organisms in a computer world called Avida replicate, mutate, and have evolved a rudimentary form of memory. Another example of evolution in a simulation lab is provided by reader Csiko: "An evolutionary algorithm was used to derive a control strategy for simulated robot soccer players. The results are interesting — after a few hundred generations, the robots learn to defend, pass, and score — amazing considering that there was no trainer in the system; the self-organizing differentiated behavior of the players emerged solely out of the evolutionary process."
Re:Not really amazing... (Score:3, Insightful)
Re:Not really amazing... (Score:2, Insightful)
What's the news? (Score:3, Insightful)
When you program some evolutionary theory in your digital world and your digital world is developing some evolutionary lifeform that is news?
Re:Not really amazing... (Score:2, Insightful)
In evolution what is important is selection, as long as there is selection (based on fitness) and variability the system will adapt to the environment (the things that shape fitness). So there is a trainer, it is called selection.
Re:Not really amazing... (Score:1, Insightful)
Indeed, the scoring function is here the trainer. The design(er) of the neural networks also helps to direct the process.
Of course, still a nice optimization problem, tuning such networks by hand would probably be a major task.
Re:Not really amazing... (Score:5, Insightful)
Saying there wasn't a trainer in the system is a bit of a misunderstanding really.
Evolutionary algorithms always makes use of a fitness function to define which generations are to survive and evolve and which are to die off, this is the case in the presented setup as well. Without knowing the project i'd guess they let the "teams" play against each other and let the winners survive.
If there wasn't a fitness function it wouldn't really be an evolutionary algorithm, evolution sorta implies "survival of the fittest" and all that you know :) The interesting part is observing the emergent behavior, in other words what we were not expecting to get out of the system. When the system doesn't have any knowledge of what a "defender" is, or what "passing the ball" means, it's interesting to see these well-known patterns evolve even when they are not specified, this is what matters to the AI researcher.
Other implementations of evolutionary algorithms may be fun (http://rogeralsing.com/2008/12/07/genetic-programming-evolution-of-mona-lisa/) but are not showing emergent behavior because you are asking for a specific output through the fitness algorithm. That is the main difference.
Re:Addendum to first article is pretty good (Score:5, Insightful)
Organisms can perfectly draw energy directly from the sun, and animals and humans still do (such as vitamin D production).
As a physician I find your statement ludicrous. While there is a photochemical step in the synthesis of vitamin D it's hardly fair calling a double bond being split by a photon as "drawing energy" from the sun. For that matter you could say that the dimerization of thymine in DNA by sunlight (which produces the genetic damage observed when a person is exposed to UV radiation) is another way we "draw energy" from the sun.
Humans do not produce ATP from sunlight. Period.
And I would agree with OP - all organisms, including plants, are directly dependent on other organisms. Without nitrogen fixing bacteria to fix nitrogen for the plants, and without decomposing bacteria to release minerals again into the soil, even plants would not exist. While the organisms that are set up to harvest sunlight directly from photosynthesis are the biggest input into the food chain, they can't live without the rest of it, especially the lowly decomposers. We're now all totally dependent on one another.
Re:Not really amazing... (Score:4, Insightful)
While true, this is also completely meaningless. For even trivial pattern spaces of, say, 512 bits, "long enough" would be far longer than the current age of the Universe.
Re:God (Score:2, Insightful)
If you look at the top scientists, most of them believe in God :)
Actually if you ask the top scientists, most of them will say they believe in God.
It's the most politically correct answer, but in their minds they are thinking 'no, dumbass, and quit asking'.
When I was young I went to Sunday School religiously. I wanted to believe, and I wanted to see the path.
After years of that, one day in Sunday School I picked up the one book it all centered around (the Bible) and asked the teacher if it was true.
He said 'yes'.
I asked if it was completely true and that all the answers were in there.
He said 'yes'.
Being fairly familiar with the book of Genesis (it was quite interesting, quite detailed, and the first chapter so I read it a few times more often than any others) and the story of the creation of the Earth, I asked if that part was true.
He said 'yes'.
So I said 'Where's the dinosaurs?' Blank stares all around.
I gave him my home phone number and said that when he had an answer for that one, call me and I'll be back. He never called. Now I'm a top scientist.
Re:Not really amazing... (Score:3, Insightful)
Interesting point. Perhaps the 'direction' comes from the sociological benefits and/or penalties for a given physical or mental trait, which could be driven internally by the system in a feedback loop.
Lets take the most basic and easily understood example today - having a child.
Does society fiscally reward or fiscally punish having a child? Both, actually, depending on where you are on the socioeconomic scale.
If you are a young and extremely poor single woman, society fiscally rewards having a child. A woman with making minimum wage at a part time job can increase her cashflow by 50% and reduce her expenses by another 50% simply by having a baby (Section 8 housing assistance, WIC, food stamps, etc.)
If you are an established and extremely wealthy single man, society fiscally punishes having a child. A successful paternity suit against a man grossing $120,000 a year in CA or MA ($120k isn't extremely wealthy there, but it's a start) can reduce his monthly available cash after taxes and fixed expenses (rent, car payment, insurance, etc) from $2000 / month to $0, possibly leaving him at a fiscal deficit each month until he downsizes his lifestyle, simply because the state will take $2000 per month from his paycheck and give it to the mother of the child.
These are pretty radical examples, but I can see where about three generations of such disparate measures on both ends of the spectrum will have a pretty serious impact on the genetic and educational makeup of the following generations of that civilization. People today point to how the group living in poverty is growing rapidly and how the upper class is being narrowed into the hands of fewer and fewer, and never stop to wonder what we are doing to cause it to happen.
Directed evolution doesn't always mean beneficial or better. And it definitely doesn't have to mean outside or divine influence.
Re:Not really amazing... (Score:4, Insightful)
The problem space is so vast when you get into the necessary details humans take for granted:
Its so vast that it makes secure passwords look simplistic - this is far beyond brute forcing AES encryption. Even a simplified problem space is usually quite large in terms of possible combinations the only advantage AI work has is that there are no singular solutions but a large fuzzy set of solutions that are reasonably acceptable.
Say a monkey typed 99% of Shakespeare but it was wrong only for 1% of it: next attempt being random, the monkey would likely have 0% Shakespeare! There would be no convergence towards the answer. Even bruteforcing encryption rules out past attempts to avoid repeating itself but a random search does not. Furthermore, say the problem space is random - so then a 99% Shakespeare is light years away from the 100% Shakespeare, then no matter what the process for convergence (ie evolution) it is not going to converge which effectively puts you into the same situation as a random search.
The monkey typing thing is a silly way to state the obvious and sound good while doing so. "Its POSSIBLE but impractically time consuming" doesn't sound as good. These AI problems are nothing like monkey's typing - they learn and progress towards competency which is totally different! Again, they do this quite quickly since anything near the monkey approach wouldn't get there in our lifetimes (winning the lotto is more likely.)
Just because it is mindbogglingly complex does not mean it is intelligent...or that it has something we'd normally think of as a "memory" either. Its possible our brains are just pattern matching machines - and since we can only understand the most simple of such things we'll never figure it out (but could build a brain which could figure it out eventually and perhaps our brains are just an extremely fuzzy non-linear pattern match for #42.)
Re:Err... what's the news? (Score:1, Insightful)
Conway's game of Life is very volatile. Cells die really easily; nothing moves without massive deaths and births; structures (patterns) only interact successfully with precision timing and spacing, which gets much worse anytime you add another structure. It's just very fragile. I don't think it's the best example of "what is possible" with genetic algorithms.
Re:Addendum to first article is pretty good (Score:3, Insightful)
Okay, how about we try a more objective approach since you can't judge this sensibly for yourself.. 1/3rd of your comments have been moderated down, often as "flamebait". I clicked on one of them and it starts with "shut up".
Yeah, it's clearly me that "likes to argue" here *rolleyes* I'm not going to waste any more time trying to help you understand why people think you're a jerk.