ANNEvolve :: Evolution of Artificial Neural Networks

Did you know that the Annevolve project is home (well, part time anyway) to a skydiving, mouseball collecting Unix admin, Eric Anderson? Eric has been with the Annevolve project since May, 2003. As a creative problem solver, Eric is fascinated at the idea that a machine could adapt. He is very interested in AI, machine learning, decision-making, data storage and processing, and neural nets.

This article is based on an email interview between Annevolve's Eric Anderson and Mike Livsey.

Annevolve: What is it that you like about the Annevolve project?

Eric: Everybody involved in the project seems to have a very positive and mentor-like attitude about them. Even questions that seem like they may be "stupid questions", are answered in great detail and explained in a way that is fairly easy to understand for a beginner (like myself). It made me feel like I could learn and ask anything, or suggest anything, without feeling stupid or inferior. How could you ask for a better project environment?

Annevolve: How did you hear about Annevolve?

Eric: After looking for good resources on the net for "beginner" projects involving neural networks, I did some searches on Sourceforge and stumbled into it. After reading a little about it, and joining the mailing list, I realized it sounded like a good fit for me.

Annevolve: Have you been involved in Open Source projects in the past?

Eric: Yes - I have written a few tools (bsdsar, spamscan, and a few others) and also am very involved in the FreeBSD project. I am also currently involved in an open source search engine project (hosted on Sourceforge as well) called Sprawler.

Annevolve: Have you had the sense of accomplishment on this project, if so, when?

Eric: I believe so - when I saw my first homegrown artificial neural network running, and spitting out data. It's only been a few weeks since that time, and I continue to work on the code to perfect it and make it more efficient.

Annevolve: What do you want to accomplish with Annevolve?

Eric: I'd like to learn more about artificial neural networks, and how to using them to solve problems. I'd also like to be able to explain in very simplistic terms how an ANN works, and how to build your own, to a layperson or someone who has not ever used them before.

Annevolve: Where do you see Annevovle headed, and where would you like to see it go?

Eric: It's hard to say where it's headed, since much of the future of the project depends on the members present desires or interests. I would like to see the project continue to be a source of educational and informative experienced ANN designers, along with new people who have the excitement and curiosity we all had when we joined the project (and still have!).

Annevolve: Do you enjoy working with the other people on this project?

Eric: Of course! Everyone involved is very helpful, and very bright. I am thankful to have found the project and have learned quite a bit from everyone.

Annevolve: Do you feel like this project has the skills and leadership necessary to carry it through to the end?

Eric: I do feel the leadership is great, and should lead the project through time - however I hope the project never ends, and continues to help those who would like to learn and understand ANN's in more detail.

Annevolve: Where are you from and where are you now?

Eric: I was born in Minnesota (USA), and now have lived in Austin, Texas (USA) for over 14 years. No - we don't wear cowboy hats.

Annevolve: We all know that this project is volunteer, unless I am the only one not receiving a paycheck, so, what do you do to pay the bills?

Eric: You aren't getting paid? Oh. I'm a Senior Systems Administrator for an x86 processor design company.

Annevolve: Where can you be found on the weekends? Skiing? Surfing? Fragging? Racing cars?

Eric: You can find me at the local drop zone jumping from perfectly good airplanes - skydiving. At night, you might find me fragging (or getting fragged) on an Unreal Tournament 2003 server.

Annevolve: Do you collect anything that is considered weird by some people? Pez dispensers? Lunch Boxes? Barbies (I hope not)?

Eric: Barbies. Just kidding. Actually, no, I don't. The closest thing I have is a small collection of mouseballs. Don't ask.

Species Learning and a Hypothesis About Brain Learning

Author: Mitchell Timin
Posted: 10/02/2003

When doing GA, expect a very large variance in the time required to accomplish a certain amount of evolution.

Author: Kent Pault Dolan
Posted: 09/09/2003

An Aspect of Natural Evolution

Author: Mitchell Timin
Posted: 08/31/2003

Genuine Artificial Intelligence :)

Author: Mitchell Timin
Posted: 08/27/2003