Podcast: Play in new window | Download (Duration: 5:33 — 3.2MB) | Embed
Evolutionary approaches, genetic algorithms, and neural networks aren’t the only approaches to creating artificial intelligence. Today, we look at one of the early and rather successful approaches—expert systems.
Podcast: Play in new window | Download (Duration: 4:30 — 2.5MB) | Embed
In the past, new methods of creating an artificial intelligence have garnered interest and enthusiasm. Then, when the over optimistic forecasts fail, nearly all funding and research grinds to a halt. It’s called an AI winter. Despite such setbacks, the general trend has been toward increasing ability and complexity within AI systems. Spring is coming, and maybe, it’s already here.
Previous post in topic
First post in topic
Table of contents
Adding by subtracting
There won’t be posts after this one on this thing for a couple of weeks. I must navigate the dangerous, relative infested waters of the holidays.
I need to be able to show that the way we program our machine can be made to run any program, at least in principle. On the other hand, I’d very much like to switch gear, and get to talking about gear soon.
Here’s one more post on using subleq. I think that will do for now.
…
Podcast: Play in new window | Download (Duration: 7:35 — 4.3MB) | Embed
In 1957, Frank Rosenblatt came up with the perceptron. The perceptron is a simple neural network that was able to recognize simple shapes. Unfortunately, Rosenblatt got a little over excited, and made over inflated statements about what his perceptron would be able to do. After the 1969 publication of Marvin Minsky and Seymour Papert’s book, “Perceptron,” which debunked many of Rosenblatt’s claims and pointed out some of the inherent limitations of the perceptron algorithm, interest and funding for neural networks dropped drastically.
Here are a couple of articles about the perceptron and the early history of neural network design.
Podcast: Play in new window | Download (Duration: 9:34 — 5.8MB) | Embed
In the early 1990/s, a biologist named Thomas Ray created a computer program that acted like a computer infected with many little programs. He called it Tierra, Spanish for “Earth.” The little programs could, and did, mutate, self-replicate, and evolve in strange and wonderful ways.
Here’s the home page for Tierra.
Here’s a good article about Tierra.
Artificial Life – Tools Ideas Environment
And here’s a nice video on the Tierra system, and the story behind its creation.
Previous post in topic
Next post in topic
First post in topic
Table of contents
There seems to be a tradeoff.
On the one hand, you can have a complicated machine, and easy programming.
On the other, you can have a simple machine, but the programming gets weird and obscure.
…
Podcast: Play in new window | Download (Duration: 6:14 — 3.9MB) | Embed
In 1984, the game Core Wars was written and introduced to the public. Contestants write programs in a special language called redcode, and attempt to halt or overwrite the other programs in order to be the last game standing.
Here’s a beginner’s guide to redcode
The beginners’ guide to Redcode
Here is a link to a page that has html versions of the original scientific American articles that introduced the game.
A. K. Dewdney’s Scientific American Articles on Core War
Here are a couple more links to pages about the game.
Podcast: Play in new window | Download (Duration: 4:52 — 3.1MB) | Embed
In the summer of 1961, a game was created. It was a programming game. Players would write programs that would compete against one another to try and copy themselves as often as possible, and attempt to deactivate the other programs.
Here are a couple of links with more information on the game.