Slashdot Mirror
The First Evolving Hardware?
Masq666 writes "A Norwegian team has made the first piece of hardware that uses evolution to change its design at runtime to solve the problem at hand in the most effective way. By turning on and off its 'genes' it can change the way it works, and it can go through 20,000 - 30,000 generations in just a few seconds. That same number of generations took humans 800,000 - 900,000 years." The University of Oslo press release linked from the article came out a few days ago; the researchers published a paper (PDF) that seems to be on this same technology at a conference last summer.
I, for one, welcome our new evolving hardware overlords.
God, I am so sorry, but it needed to be said...
For once Skynet jokes will be on topic!
Shh.
My computer been evolving for the last ten years. Started with an AMD K6 233MHz CPU, 32MB RAM, and a Nvidia TNT 16MB video card. Now I have an AMD Athlon 64 2.2GHz, 1GB RAM, and a Nvidia Geforce 6200 128MB video card. I'm just waiting for the power supply to evolve so the system can support an ATI 512MB video card.
Call me back when I can start a culture of Core Duos in a petri dish filled with a silicon nutrient.
DYWYPI?
And it's been done before - at least once - http://www.newscientist.com/article.ns?id=dn2732 - there's another one too, but I can't find it right now. Crazy stuff though.
lemonade was a popular drink and it still is
At first glance, this is supposed to impress us with the hardware:
By turning on and off its 'genes' it can change the way it works, and it can go through 20,000 - 30,000 generations in just a few seconds. That same number of generations took humans 800,000 - 900,000 years.
In fact the simplest DNA based organisms/structures (bacteria, virii) have the shortest "life span". The number of generations per sec. isn't anything to brag about.
All complex organisms have some sort of lifespan longer than a microsecond. For a good reason: people pass on knowledge and adapt *during* their life span (not genetically of course, but our brain allows us to adapt a lot without such).
Hype aside, interesting development, but I wish those publications wouldn't use misleading statements in pale attempts to impress us.
Bah! It ain't in the Bible! Next thing you know, you'll be telling me that Programs don't believe in the Users, and that we should just blindly accept the secular rule of the Master Control Program.
That's it... isn't it? It's all just an MCP trick!
Well, I still believe in and will fight for the users!!
Thanks,
Mike
I won't go into details here, but anything that can be implemented in hardware can be done in software and the other way around too. This is a nearly ancient Electrical Engineering principle.
In the era of programmable logic chips that can alter their own logic (the patterns are stored in RAM or flash RAM for crying out loud), this isn't even that big of a revelation. Indeed, Transmeta has been doing stuff similar to this and selling it commercially for some time. They just aren't using these cool buzzwords.
And evolving architechtures is something that I know has had some serious CS research since the early 1970's and perhaps even earlier. I don't think an idea like this is even patentable based on this earlier work in this area. I bet you could find some adaptive systems that were even build specific for the oil industry, which would defeat even a narrow claim of that nature.
Where the money to be made off of this sort of technology is on Wall Street or other financial markets. I even found a web pages from a research group of adaptive systems that said essentially, "We have discontinued research along these lines and are now working with an investment firm on Wall Street. Since we have all become millionaires, we no longer need to support ourselves through this project, and any additional details would violate our NDAs." I'm not kidding here either. These guys from Norway are not thinking big enough here.
Crazy stuff indeed.My favourite bit:
lemonade was a popular drink and it still is
But this really is old news. I'm a 22 year old snot-nosed nobody and I did "evolvable hardware" during an internship two summers ago. My mentor had started on evolved FPGAs in 1992.
I am hoping that it is the writer's fault that this article feels so gloriously over-reaching and under-specified. From the paper, it looks like they have made a good advancement. They argue that their method is more effective than previous methods by several quantifiable metrics. From the article, it looks like they have invented an entirely new field that will result in the obsolescence of humans by 2010.
As for their method: It appears that the evolved genome actually dictates a structure that is imprinted a level above the fabric. That is, the underlying SRAM in the FPGA fabric is fixed, and only configuration bits are being changed. This severely hurts their claim of "generic evolvable hardware", but is almost an absolute necessity given the chips they are using. The reason our system was so slow is that each configuration stream had to be checked for possible errors: Some configurations would short power and ground, and fabric doesn't like crowbars!
In conclusion, I believe the writer of the article should be fired, and the authors of the paper should be commended for a good step in the right direction. I'd also like to appologize for my lack of coherance: I had my tonsils out and I am therefore high on Hydrocodone.
www.olin.edu
Yeah, it was pretty amazing. They mapped out a section of the circuit that the genetic algorithm came up with and found that when analyzed as a logic circuit, a large portion of the configured part of the FPGA should have had no effect on its behavior. When they cropped that section of the circuit out, though, the rest of it mysteriously stopped working.
This was because the configured circuit operated a lot of the transistors in linear (i.e., non-saturated) mode, taking advantage of things like parasitic capacitances and induced currents. No sane human would operate an FPGA in this fashion, but since those little anomalies were present, the GA took advantage of them. That's a recurring theme in GA research: if you are running a GA on a simulation, for example, and you have a bug in your simulation code, it's fairly likely that the GA will find and exploit that bug instead of giving you a normal answer. See Karl Sims's research from 1994 for some amusing examples of this.
Sadly, Xilinx discontinued that particular FPGA line a while back, so if you can't find some old leftovers of that part, you probably won't be able to recreate the experiments yourself (the research was originally done a decade or so ago). This is because that particular device had the advantage of being configurable in a random fashion without risk of burning it out due to things like +V to GND connections. Of course, Xilinx considers their programming interface to be proprietary, so I don't know that you'd be able to recreate that work even if you did manage to find the right part.