Blogs

Although, as Doug pointed out in class, there are important differences between connectionist networks on computers and neurons in the brain, I still think that the name "Neural Networks" is justified by the fundamental similarity between the two. This fundamental similarity, which I think is very important and which also implies many promising possibilities for simulated neural nets--based on phenomena in the brain--that have not yet been explored in AI research, ...this fundamental similarity is the way in which information is manipulated through destroying some info and then copying the result and distributing it to create new info. That is, when the activations of input nodes in a computer network are summed in a node, which node each of those signals came from is lost. But the information that remains--the combined strength of those inputs--is then copied and distributed to nodes in the next layer, where the process is repeated. I think that this method of information manipulation is an incredibly important concept in and of itself; therefore, we should acknowledge connectionist networks' debt to the structure of the brain. Furthermore, I think there is (or will eventually be) a lot more we can do with neural nets based on observations of how the brain works.

I know this class is about emergence, but since we're frequently dabbling in the area of artificial intelligence, I feel like I can't pass up the opportunity to post this. I came across this site last year and recently rediscovered it today. It's an interesting chess-playing AI applet called the Thinking Machine 4. When it's the computer's move, it searches the board for the best move; what makes this interesting is that while the computer is "deciding" it's move, it actually maps the possible moves and counter-moves with colored lines. It reminded me of the idea of how an agent should determine how its actions change the world around it--which is something we discussed in Intro to AI. As the gameplay progresses, it's evident that the program makes more specific moves. I don't know if I would quantify this as intelligence though. Could it be that the search tree the program is traversing is becoming smaller? The method by which a typical AI program uses to quantify a 'good' move doesn't usually change during a game--to my knowledge at least. With that said, it's hard for me to say if the moves are becoming 'intelligent' or if the 'good' moves are just a product of the current state of the board. On a more technical note, the programmers used something the quiescence search method in conjunction with alpha-beta pruning in order to cut down on the size of the search tree. It's pretty neat, so check it out. Enjoy!

Today, one of my favorite biologist bloggers pontificates on Conway's Game of Life, agency, and the biologist's job of finding patterns. Pharyngula explores the development of complexity in Chance and regularity in the development of the fly eye. When Pharyngula (PZ Myers) argues against a magical interpretation of the unfolding of events, he is talking to the "intelligent design" proponents who would point to this development and claim that it must be the act of a designer.

I thought I would link you all to the website I demonstrated Monday in my report about Blink. This is the Project Implicit website, where you, too, can spend time freaking out about how prejudiced you are, probably about groups that include yourself. (For example, I happen to "fail" the Gender-Career test miserably.)

In computer graphics demos there is a fairly common method of rendering water ripples based on a CA; each cell has a height value, and every frame its height value is set to the damped inverse of its previous height value + the average height of its neighbors. This results in fairly realistic-looking ripples that propogate outwards as expected. A tutorial for achieving this effect can be found here. In my game I am implementing a fairly similar effect for water ripples.

Only because Pi has come up so frequently in class, I thought this article on the history of Pi might be of interest.

I figure I'll have my midterm nearly completed by about midnight Sunday...are there people interested in reading papers and providing commentary for an hour or so at around that time? How does 12AM Sunday night Zubrow Commons in the INSC sound? I'll be there then unless people suggest a BMC locale instead.

During class when everyone picked a book they were reading and doing the midterm report on, I had picked Turtles, Termites and Traffic Jams by Mitchell Resnick. But, I have been reading through How Nature Works by Per Bak and decided that I like this book more than Turtles, Termites, and Traffic Jams. I was wondering if someone in class is also reading this book for the midterm project and would mind if I used it for my mid-term project as well...

Digg, a social networking site (with emergent properties, maybe), has linked to a page boasting a set of sort algorithms faster than Quicksort. It's called Critticall, and it uses genetic algorithms to evolve C programs.

As per Doug's request, here's my revision of Doug's emergence demo code. It's pretty simple. I added a second class, the same as his but with some adjustment in the fitness function to try to account for letters correct in a row. I marked the lines I added so I could later identify my changes. I also added three variables: trials (to indicate the number of trials to be run - and to make it easier to fiddle) and old & new to keep running totals of the number of generations each needed to achieve the correct phrase.