Powered by Twitter Tools.
Achieving a scientific discovery has been the sole domain of humans for quite some time. However, artificial intelligence is starting to catch up. Enter “Adam” an artificially intelligent robot with the tools to analyze biological data, formulate a novel hypothesis about that data, derive a set of tests to verify the hypothesis and then carry out those tests, and present conclusions from the data!
Adam’s repeated experiments resulted in the system identifying a few unknown genes in baker’s yeast that work together to form an orphan enzyme, this relationship was not previously known and Adam independently identified it.
Tools like this can allow human researchers to think at even higher levels, theorizing about broad spectrum experiments and leaving the systems to explore the frontier for them.
Doing a little technical work with Automatons Adrift right now. I just upgraded the wordpress to 2.7.1. I might even change the theme. Though if I can’t find something I really like I will probably alter the code of this theme instead.
Just an FYI!
Right now we have resistors, capacitors, and incutors we also have four basic circuit variables current, voltage, charge and flux. I am not an engineer but my understanding is, that with these variables you should be able to have four different components and not just three. The fourth component known as a memristor was first theorized in 1971 by Leon Chua. This theoretical fouth component would have properties that were not reproducable by the other three components alone or in any combination.
Both New Scientist and an even more mainstream magazine Maximum PC have reported on the memristor. This component is simply that big a breakthrough!
The memristor is indeed different from its brothers. When a charge is passed through the circuit in one direction its resistance increases, when it is passed through the other direction it decreases. This amount of resistance is analog as well. This means a memristor can store values that don’t just equate to one or zero although their first use will probably be to make solid state memory that is faster than any memory that already exists and has a data density greater than a factor of ten from todays solid state memory like flash memory. It is much less volatile than flash memory as well so it will last longer, and the state of the memristor can be read using similar techniques to todays memory cirtuits so it it doesn’t require any fundamental changes to underlying hardware.
Since memristors can store large amounts of data in such a small area they are perfect for memory components in nanoscale machines, the ultimate new automata of the future. They can also double as processor components that are dynamically changed as needed. So not only can the memristor function as a memory it can be made to function as a processor as well.
Memristors due to their analog nature function very similarly to human neural networks. The memristor can retain data from reinforcement learning very easily, a few hundred memristors can simulate a full human neuron in a similar amount of space.
Memristors are truly an amazing breakthrough and could lead to a paradigm shift in toadys technology.
Yep, it is been a while since I blogged. You start playing a game with a highly addictive nature, and blamo, you haven’t blogged in a couple months.
That’s ok though, there have simply been too many cool breakthroughs the last couple weeks that I just couldn’t ignore and I had to blog about. Keep an eye out for posts, they are starting again.
Moving through busy environments is a complex task that is becoming increasingly easy for computer systems to perform on the groud. The task is made even harder while flying if you want to fly low to the ground. New obstacles become serious problems, like power lines and overpasses. A team at Carnegie Mellon University have modified a UAV to fly low to the ground successfully.
The UAV can have a pre-loaded map or it can build its map as it flies using its laser range finder sensors. The lasers sweep an oval pattern out front of the vehicle and develop a dynamic map. If an obstacle is detected the system plans a route around it. Current UAV’s cannot fly low to the ground because they lack a system like this. This new system is planned for deployment in unmanned medical rescue helicopters.
Probably also for highly tactical seek and destroy missions too, but I will hold out hope that it is only used for the rescue helicopters.
We have talked about the turing test before, now it appears the US Army wants to give it a shot in World of Warcraft. Along with several other advanced technologies like regenerating body parts, erasing bad memories, and electronic telepathy they are attempting to develop virtual soldiers that look and behave like a real human.
To test these virtual humans they are going to deploy them in World of Warcraft. The virtual soldiers should be able to convince humans they are real, going as far as emulating emotion and using local slang correctly while responding to questions and communicating effectively with other players.
It appears the Army is attempting to tackle some very complex AI and Nanotechnological problems. If one of their AI soldiers does manage to fit in properly in World of Warcraft, how far off is it from passing a full Turing Test? Does it have full understanding and is able to relay tactical situation information back or does it just manage to fit in without any higher awareness of its situation?
They may be biting off more than they can chew, however the Army/DoD have been responsible for several massive technological advances. Anyone ever hear of this thing called the internet?
Over the last week or so I haven’t seen many breakthrough bits of research that I wanted to share with Automatons Adrift. I have been reading the papers from AIIDE 2008 and some of them have been very interesting. I will share a synopsis of some of the cool ideas shared at that conference in a later post.
Now there has been a song from the void. The automatons are singing, or at least trying to sing. A UK researcher has been experimenting with autonomous agents that communicate through singing and work together to improvise a song or melody. The robots currently attempt to mimic eachothers sounds and it has been scaled up to twenty robots. Further research in this field can be applied to group communication and organized planning.
This is the type of research that can be applied to swarm intelligence, smart dust, and many other distributed systems that required communication and innovation.
Congratulations to my American brothers, I believe your world just got a thousand times better. Now let’s all work together and make the world as a whole an even better place.
What is the Singularity? Ever hear of Moore’s Law?
If you are reading this blog you probably have. Moore’s Law is an informal law about technological advancement. In a nutshell it states, that every 18 months or so, the power of computers doubles. Computer power has been following this trend for 40 years and it is set to continue following it for another 40 years. The idea of the singularity is, if technology does indeed continue to double at this rate, in another 40 or 50 years the sheer power of the computing systems available will so far surpass mankinds abilities that the formation of an artificial mega intelligence will be impossible to avoid and it will be a new age of evolution. Of course, this new age could go the way of Terminator or we could essentially all become godlike through unimaginable advances in AI, computing power and Nanotechnology. A lot of pieces need to fall into place for it to happen but many people are starting to think it is inevitable.
Don’t agree? Intel thinks the Singularity is a real possibility. Don’t think computers will ever really get that powerful? How about a super computer for your desktop by Cray? While Cray hasn’t released performance specs for this system it is bound to be more powerful than their first super computer. In fact, your common desktop today is roughly two hundred times faster than the first Cray. While this computer still cannot model the entire human brain that doesn’t mean anyone isn’t going to try. IBM’s Blue Brain project plans to model the human brain in its entirety in the next ten years. Is that enough to form a mega intelligence and bring about the singularity? Probably not, but it is getting closer.
The 2008 Singularity Summit is happening this friday. Some of the worlds greatest minds in AI, Nanotechnology, Innovation, and The Singularity will be there. Who knows what interesting ideas will be shared at the conference this year. Typically video’s of the conferences talks are available after the conference for anyone who is interested.
We can’t know for certain what the future holds, like I said, a lot of pieces need to fall into place for the singularity to happen. Will Nanotechnology advance the fastest and allow us to transform humans into fully cybernetic entities thus creating mega intelligent computer systems out of our own consciousnes? Will computers advance to a point where we create true AI? This AI would have access to our vast stores of knowledge, it would have the ability to instantly learn and integrate new knowlege and then could develop new theories based on that knowledge. It would be able to optimize itself, and duplicate itself creating more and more AI’s. These new AI’s could allow the advancement of Nanotechnology to the point where we could join them in their electronic virtual playground if we so chose to. Or maybe neither will happen, due to economic and political stresses. We just don’t know.
I for one welcome our future mega-intelligent overloards.