Slashdot Mirror
CAM-Brain: Artificial Self-Teaching Brain
lostkluster writes "Genobyte is developing Robokoneko, a kitten (at first, computer simulated) to use CAM-Brain technology, a self-teaching artificial brain with a goal to have billions of artificial neurons by year 2001, but as a first step, it will have 32,000 evolved neural network modules. The CAM-Brain project is even to enter the Guinness book as "Most Powerfull Artificial Brain".
More news and info at Prof. Dr. Hugo de Garis homepage (head of the Brain Builder Group at ATR), and at whatis.com. "
So is this another way of escalating the cat and mouse game. You dont need a smelly cat anymore. You can just turn on the kitty and say find me a mouse and remove it from the house. Gotta love technology.
Good is never enough, when you dream of being great!
... then this is perfect. Of course, a Robokoneko looks like it could kick Aibo's metal ass. Of course, any virtual robot is going to seem cool when compared to one that exists.
I think we've found the subject for our next flame war.
Questions I have:
a) These CA Modules.. Are they discrete units? Are you just tossing a bunch of gates onto a chip and then connecting them randomly or what? Details, man.. All I wanna know is what you consider to be the "individual neuron".
b) How the hell are you gonna get a billion of these inside that little cat thing, and still have room for wiring, motors, etc. Build something bigger, like a good sized tiger that you can ride around.
---
- Give a man a fire and he's warm for a day, but set him on fire and he's warm for the rest of his life.
Only you can prevent the /. effect.
There's a European mirror at http://foobar.starlab.net/~degaris/
Why dont you play "last post", where you wait until just before an article goes static and try to be the last one posting to it. You will be very 31337 and it wont bother anyone else. I promise. :)
They sound pretty optimistic. They have yet to do a 32'000 'neurons' based unit and they already think they can do a one billion unit within a year of the 32'000 one?
32000*1150~36000000 = ALOT of braincells to simulate.
This brings to mind the science-fiction idea of storing human consciousness via mechanical means, and having that machine consciousness interact with the world (I'm thinking of Greg Bear's Eon series, for example). Would the billion neuron model be strong enough to start this line of enquiry, or is there still a lot about human neural mapping that we still don't understand?
Heavy on the jargon and schematics;details, publication history absent. Its a couple of orders of magnitude larger than what other people have tried, without a clear design. I think it is a scam aimed a bilking Japanese investment house who suck up to anything dealing with cute robots.
I don't really remember the specs for sony's robodog (what was his name?), but this thing sounds, um, very superior. Besides, I dont think sony's dog could "learn", right?
:)
Well, one more step towards towards terminator 2
Joseph?
They're project is headed making a "real"-like artificial brain, capable of learning on rules... I think it's way too much serious than aibo.
Stop comparing them! =]
Sorry, but im still under the impression that these scientists were preoccupied with the technology, not with the reprecussions. Don't get me wrong, this kitten is cute as can be, but has anyone here ever heard of wintermute? the matrix? terminator? Im not sure i want (like the website on the link says) within a few decades neural networks that are much more complex than the human brain. I want to still be able to pull the plug before they get smarter than us. Call me paranoid, it dosen't mean they aren't out to get me.
Agreed! we need more laser fights.
A comment was made about moview like the matrix, terminator...etc. Where ai becomes stronger and more intelligent than us, and they take over. Well, those are very real possabilities, but it also cannot be prevented, nor should it be. We are going to create a ai neural system that will have the potential to far surpass our natural biological potential. That is fact. Due to it's nature, it will produce major improvements for itself and it's new offspring that it creates...without human intervention. We are going to have to adapt to that in some way. If the potential for technology is there, but the only obstacle is fear of what it will do... that obstacle will be surpassed ultimately.
So you want to kill everyone that's smarter than you?
Being (along with the rest of earthlife) laughably stupid I wouldn't mind to have someone think through difficult things and explain them to me. Just like I don't at all mind having a calculator divide 78646/427 for me. And I most certainly don't want to 'pull their plug' because the can calculate better than me.
The developper does not appear to be Japanese. The 'bot isn't being developed in Japan. The name seems to have been chosen for the sole purpose of misleading, probably to play off of Sony's Aibo. Maybi I should start on my own artificial life form and call it mezumibot? Dou kashira?
I had an opportunity to speak with Dr. de Garis over a year ago at a party thrown by an acquaintance of mine who had interviewed de Garis for a documentary on Nanotechnology and AI. I found Dr. de Garis intelligent, personable and amusing.
At the time he was rather pessimistic about the Robokoneko project, but mostly because of the cultural problems he was dealing with as a Britisher in Japan. However he claimed that the artificial neuron work was proceding well, even though they were doing it all with simulators. He predicted then that, before 2000, they would be creating silicon versions. From the information in the links it would seem that his prediction has come true. Only they are using FPGA chips instead of going to a foundry for CAM specific VLSI.
It is interesting to note that Dr. de Garis has made incredible progress by following a path the mainstream AI community has largely discounted -- that of modeling real neurons and real brain structures. I wonder what will come out of his next collaborative development at Starlab in Brussels? From his statements to me I would certainly hope he would find the living and working arrangements more congenial.
I do find it very interesting that he will be working with Lernout and Hauspie (developers of Voice Recognition software). The spin-offs from that may be more important than the original research!
Jack
- -
Are you an SF Fan? Are you a Tru-Fan?
Reading the detailed paper, I can't help but see this "cat/brain" as essentially an implementation of Rodney Brooks's subsumption architecture. Maybe the "cat" will be capable of a few reactive behaviors, but it'll be just as brainless as it's technical soulmate Cog. The real breakthrough in making an artificial brain will be when we figure out how to do it (i.e. what the architecture is), not when Moore's law brings the number of neurons or processing power within reach.
"It is interesting to note that Dr. de Garis has made incredible progress by following a path the mainstream AI community has largely discounted -- that of modeling real neurons and real brain structures. I wonder what will come out of his next collaborative development at Starlab in Brussels? From his statements to me I would certainly hope he would find the living and working arrangements more congenial."
Umm, no. The reason people stopped trying this is that (1) we can't model everything about the neuron (2) what we did try didn't work (3) we don't know how real neurons learn.
This is probably a big backpropagation net on a chip, thus after 10,000 trials it will learn some stuff, while forgetting everything else that it learned before. If you ask connectionist people if the brain is a big set of backprop nets and nothing else, they will say "no" (notably among them would be McClelland).
The AIBO's sony sells adapt their behavior paramaters, but don't really learn. The modified AIBO's in Robocup had some learning. For example, the team from CMU (which I worked on) had a vision system that would learn in a limited way.
Machine learning right now depends mostly on the fact that problems are well broken up... Large scale, full "perception -> action" systems have so far been simplistic in what they learned, slow, or largely unsuccessful. I'll believe results, not speculations.
Hard, Sobering Facts:
All they've evolved yet is some primitive motions in a simulator. Rodney Brooks & Co. did that on a real robot several years ago. It was by no means a trivial task.
It took Sony around 2 years to get a mobile quadruped working in the real world, after they already had a simulator for it in which it worked just fine.
Repurcussions are for science-fiction writers. :)
... nor would it necessarily be a good thing to do so: for each of the nightmarish uses I can imagine all of these things being put to, there are an equal number of incredibly good uses, as well.
... which probably makes the potential for a mistake more scary, because it's a risk we don't _have_ to take ... except that naybe we do.
Seriously, though: there are a lot of technologies currently being researched which have disturbing implications --- mite-sized cameras which can move themselves around; plastic-eating biotech creatures; energy generation from radioactive waste; artificially grown organ replacements; etc, etc.
These are all being actively researched. Some will pan out in the near future, some will remain as mythical as the flying car. But either way, there's too much money, and too many people who think the technologies are cool, to stop them
As for AI? It's hard to tell, because it's hard to imagine what the use value of these experiments are right now. Some of the side-effects are clear: neural net technology could make things like internet search engines actually usable, and a friend of mine was recently talking about an interesting neural-net tech possibility that could provide a cure for writer's block. But in general, it seems like playing
Maybe we have to know if we can do it. Maybe, as has been suggested in numerous science fiction novels, maybe this is essentially evolution happening before our eyes, only we are creating the next step. Who knows? Don't you want to find out?
I realize it's a long way off yet, but as a profound cat-lover and techno-geek, I'd kill to get one of these.
:)
"A cute little robotic pet that's fun to be with!"
And it mimics a real-life kitten? As long as they make it unbelievably cute, I'm hooked.