All Things

New Scientist is reporting that Ramesh Sharda at Oklahoma State University has developed a practical neural network (artificial intelligence) program that 75% of the time can successfully predict, within a fair degree of accuracy, a film’s theater receipts.

The interesting thing about this to me is that Sharda has apparently gotten the neural net to identify seven key parameters that reliably predict film receipts. He fed a large database of hundreds of films into the neural net, effectively “training it” (which is how neural nets work), presumably with initially many more than seven parameters for each film.

While being able to predict a film’s success would certainly be useful information, simply being able to identify a limited set of key parameters for a given activity could itself be highly worthwhile. For example, say a restaurant chain such as McDonald’s wants to improve their real estate selections. Presumably they would have a large database of sales information that they could plug into a neural net, which might then be able to pinpoint which parameters are truly key (e.g. traffic count, demographics, proximity to other restaurants, etc.).

If certain parameters over which the company had control could be found that would yield substantial improvements, then this might better guide improvements to present locations (or processes, products, etc.), while the neural net could be used to analyze future potential locations.

In general, the state of the artificial intelligence field seems pretty obscure nowadays. I’ve been wondering lately whether many practical applications are finally taking hold, and whether these involve neural net technology or some other approach. In the mid-80s, languages such as Prolog and Lisp were being touted as tools for building elaborate knowledge bases, etc., but I wonder if anyone is still working with these.

In the second half of the 80s, neural nets seemed to pretty much eclipse language-based artificial intelligence. Way back then I took a serious look at Prolog, which the Japanese had favored for their research. The notion of declarative programming still fascinates me, but without a background in predicate logic or computer science I didn’t have much confidence in my assessment. For one thing, I never could see how one would go about debugging a Prolog program!

I’ve written some about the Tuskegee Airmen on my site AeroGo, and about efforts underway to preserve their history.

I also noted how I’ve been surprised journalists haven’t given much coverage to Star Wars filmmaker George Lucas’ indications in interviews (such as with Charlie Rose) that he’s working on a film about the airmen, and that it’s something he’s wanted to do a long time.

Friday I finally got around to taking out our birthday boys (2 in July). One stop was to see the fairly new Imax film Fighter Pilot. We saw it in a 2-D theatre; I don’t know if it’s also in 3-D or not. It’s about the U.S. Air Force’s Red Flag exercises, which are based at Nellis AFB in Nevada and similar to the Navy’s better-known Top Gun school.

I was impressed with how many aircraft they managed to fit in roughly a 48-minute film. Of course there were F-15s, -16s, and -18s, but the A-10 also got a lot of coverage, as well as an E-? AWACS aircraft. The AWACS displays were really impressive, but it still looked like it would be hard to keep track of all those aircraft in the sky.

Apparently Red Flag is a substantially larger-scale wargaming operation than Top Gun, or maybe the film just didn’t distinguish that from the training. There were quite a few other aircraft shown briefly. Some of my favorites were of the B-1, the F-117 (I like its looks more and more over time!), and of course the cockpit views.

One thing I couldn’t help notice is how many flares are used nowadays, to counter potential IR missile threats. I wonder whether all that is controlled by software or just the pilot. One thing they were trying hard to convey was the sense of how much firepower these machines carry, but I don’t really think they succeeded there.

Helicopter gunships and A-10s are awesome fighting machines, though now increasingly vulnerable to ground attack. I have seen A-10s doing a lot of low-level maneuvering in Louisiana, near Ft. Polk (perhaps the aircraft were from Barksdale). Those aircraft can make a run, turn and come right back. It must be truly awful to be attacked by A-10s or some of the big helicopters such as the Russians used in Afghanistan. After going through that I don’t doubt that a lot of those fighters (some now our enemies) really are tough.

It’s hard to complain much about what wasn’t covered because of the film’s length. Overall, I liked it quite a bit. The best parts were definitely scenes of aircraft in flight. If you like aerospace, and have been working too long lately, it might just be the something different you need for a break. I definitely would like to see it again if in 3-D.