Adrift in the silence, but now a melody from the void

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.

The dawn of a new age.

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.

Desktop Super Computers and Singularity Friday

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.

The Neuroevolutionary Solver documentation updated.

The Neuroevolutionary Solver “How to install and run” section is pretty much complete. These instructions should make it easy to get a NS environment up and running so you can perform your own experiments. More updates to come in the future, making the NS one of the easiest systems to use for Evolution of Artificial Neural Networks.

Neuroevolutionary Solver Version 1.01 Available – Bug Fix.

So sometimes when you are working on some code, you like to write a little bit of debugging code and build it into your system so you can confirm that a component is working as it should.

I had built such a piece of code to be certain that the artificial neural networks we use as phenotypes are consistent between generations. The code confirmed that structurally they were consistent and that their output is consistent after one step of evaluation. The first evaluation of the reformed network has not propagated through the network completely and consequently the very first set of outputs of your neural network are not as precise as they were in the previous generation. The second evaluation puts the neural network back to its original normal state. In a future iteration of the system I plan to initialize the networks once before they are placed in an evaluation environment eliminating this slight variation.

Having said all that, the code that verified these phenomes itself had an error. An errant semi-colon was placed at the end of an if-statement which forced the debug code to run for all NEAT experiments instead of just NEATforXOR experiments.

The bug has been fixed and all the downloads on the Neuroevolutionary Solver page have been updated with correct versions of the code.

Bugs are fun!!!

I used to grow crystals as a child

When I was quite young my mother gave me a grow your own crystal kit. It came with a bag of Alum and instructions. I first had to grow seed crystals in a super saturated solution of Alum and water. Then I placed the best seed crystal at the bottom of a jar and covered it in another saturated solution of Alum. After several weeks I had a fairly nice big crystal, formed from my seed crystal. It didn’t do anything except look pretty.

Scientists have really stepped that up a notch with these Self-Assembled Orgaic Circuits. In order to form these complex structures they create a silicon dioxide substrate with gold electrodes using conventional techniques. They then submerge the substrate in a solution containing the organic semiconductor and the molecules arrange themselves on the substrate in a densely packed single layer of molecular layer. Prior work has developed faster circuits but this method is extremely easy to deploy.

This type of technology will allow complex electronics to be embedded in items where it was previously not possible. It opens up the possibility of structurally flexible electronics that are cheap and easy to assemble. You may have a computer directly embedded into things like coffee cups, cereal boxes, newspapers, or have portable display devices that can roll up or fold up without complex engineering requirements.

Very cool future possibilities.

More useful junk

In a paper published today in PLoS Genetics the research supporting the value of so-called junk DNA gained more ground. As is stated in the article biologists have known about junk DNA for many years but it was felt that it was mostly extraneous data in the genetic code.

If you have read the research behind SDNEAT, you know that scientists are starting to change their perceptions of junk DNA. Segmental duplications seem to be critical in the evolution of species, they allow for high levels of genetic variation and mutation with a smaller chance of disabling the original genome all together.

This new study suggests that DNA ‘retrotransposons” are important to human evolution. One specific set of retrotransposons are called Alu elements:

“Alu elements are a major source of new exons. Because Alu is a primate-specific retrotransposon, creation of new exons from Alu may contribute to unique traits of primates”

Perhaps as an extension to SDNEAT the algorithm to merge a segmental duplication into the genome being mutated could be extended to allow for transposition of the identified segment within the genome. These higher order mutations could be exceptionally valuable when dealing with extremely complex solution spaces and genomes.

Autonomous Helicopters

These automatons are certainly not adrift but they are definitely airborne and capable! Computer Scientists at Stanford have developed an autonomous helicopter that can learn from a human expert pilot to perform complex manoeuvres better than the original human expert!

The learning system does not just copy the controls for performing the manoeuvres it watches several built in sensors for the state of the environment around the helicopter and through several iterations develops an algorithm that can handle situations that were not part of the training but allow the autonomous pilot to complete the manoeuvre. These adapted agents could even keep more precise control over the aircraft than the original pilot could.

“For five minutes, the chopper, on its own, ran through a dizzying series of stunts beyond the capabilities of a full-scale piloted helicopter and other autonomous remote control helicopters. The artificial-intelligence helicopter performed a smorgasbord of difficult maneuvers: traveling flips, rolls, loops with pirouettes, stall-turns with pirouettes, a knife-edge, an Immelmann, a slapper, an inverted tail slide and a hurricane, described as a “fast backward funnel.”

The pièce de résistance may have been the “tic toc,” in which the helicopter, while pointed straight up, hovers with a side-to-side motion as if it were the pendulum of an upside down clock.”

I know I can’t do any of that and I certainly couldn’t learn it quickly. Could the learning system that Ng and his team have created be adapted to driving cars and flying planes? Possibly, as it depends on if it uses any assumptions about its environment. Flying around in a big open space is much easier than driving quickly through busy city streets. That doesn’t mean it can’t be done. The only downside to this research is it could be used to pilot Autonomous military planes to deploy weapons, completing the conversion of war to a video game.

Hopefully we see this deployed for peaceful use instead.

Evolution of the Neuroevolutionary Solver documentation

There was some major updating of the Neuroevolutionary Solver page on the weekend. Now there are sections to help you download the software, install the required Java JDK and Java 3D packages and instructions on how to get the NS working on your home system. Working with the NS is much easier through the Eclipse IDE and detailed instructions are available for that method. Command line instructions for Windows and Linux are also available. Click through to the NS page here or click the Neuroevolutionary Solver tab at the top of this page.

Keep watching for more updates over the next few days.

The Learning Algorithm of the Brain

A group of researchers at NYU have been given funding to “discover the learning algorithm of the brain“.

This will be some exciting work, many scientists believe the easiest method to general artifical intelligence is through duplicating the human brain, that the sum of the parts is the soul so to speak. These researchers will be focusing on the visual system and how it manages to identify all the important bits in a photograph or any real world scene. They will then apply what they learn from these experiments to see if the same methodology works on similar brain structures.

I am not certain but this research may be related to the recent full simulation of the human visual cortex on Roadrunner currently the most powerful computer in the world. This full simulation of the visual cortex was a simulation system called PetaVision which actually was a full simulation of all the neurons that compose the human optic system and visual cortex that could be run in real time.

Slap some ears on it, a nose, and a neocortex and we have a beautiful baby AI.