Jump to content
  • Advertisement
Sign in to follow this  
  • entries
  • comments
  • views

Some interesting reading

Sign in to follow this  


I was looking for some fairly easy to grasp paper on what is intelligence and I think I found a neat one. It a neural network flavor due to its author, Paul Werbos. Here is the link.

For those who don't know who Paul Werbos is, here is a little biography (which I have copied from a website--backpropagation is the learning technique I use in the previous multilayer neural network code I made):
Paul J. Werbos is best known as the original inventor of backpropagation, as part of his Harvard PhD thesis, which was reprinted in full in his book the Roots of Backpropagation, Wiley 1994, along with his classic 1990 tutorial on backpropagation through time for Proc IEEE. He was one of the three original two-year presidents of the International Neural Network Society, and winner of the IEEE Pioneer Award. He is Program Director for Control, Networks and Computational Intelligence at NSF, which actively seeks more proposals in this area. He has also been active in many cross-cutting funding initiatives; for example, he serves on the Working Group for energy storage and distribution of the interagency Climate Change Technology Program, and coordinated the NASA-NSF-EPRI solicitation on space solar power (NSF 02-098). He is also on the Planning Committee of the Millennium Project of the United Nations University (http://millennium-project.org), and has published a few papers on quantum foundations and technology (see arXiv.org, physics and nonlinear systems). He also has two degrees in economics from Harvard and the London School of Economics
Sign in to follow this  


Recommended Comments

Oi! Ive read that paper before I have. Its a whole load of nonsense it is.


Just kidding, that paper or a similar one has been on my to read list for some time but Ive never gotten around/been to lazy to reading it but I couldnt help myself. hehe.

Share this comment

Link to comment
hehe.. yah it is a long paper.. I'm still searching for more...

"Don't stop... believing.... hold on to that feeeeeellinggggg..."

Share this comment

Link to comment
If you haven't read it before Gödel, Escher, Bach: An Eternal Golden Braid by Douglas R. Hofstadter is a very interesting discussion of what intelligence is.

There's a webpage here for the research team but it's not updated all that much. It's not too hard to hunt down the papers if you don't fancy the book. The books interesting on it's own (and extremely entertaining and well written) but the papers are were the technical details at. Most of the programs have their source code available too, in scheme I think.

Now and again I find myself wondering how you could put the "The Parallel Terraced Scan" somewhere into a game.

Minsky is interesting to read too.

Sorry if you're not talking about "strong AI" :D

Share this comment

Link to comment
Thanks for the link. I've actually been thinking of using intelligent agents in a game. Haven't come up with anything yet either. I'll have to go back and investigate the papers when I get the time. It looks like a refreshing drink of water (I wonder if a computer will ever make a statement like that--nah, probably it would say... "Upon examination, the subject is different than those things I have examined in the past.")

Share this comment

Link to comment
Interesting article.
Though in my opinion he overlooks the the fact that the mammel brain workes in a rational manor which the human brain not always does.
A gazelle in africa acts rational when it sees a lion. It runs.
A man buys a Mercedes. from a economic standpoint that´s probably not a rational decision.
Human beings sometimes act/think irrational which sometimes sparks great ideas and what not.

What if game ai sometimes acted irrational ?

Share this comment

Link to comment
I'm not sure classifying decisions as irrational or rational would be beneficial. It might be something closer to imagination or what I like to think of as "searching the knowledge space" or "modeling the world" That would make more sense to me. Now if we say there are bad and good decisions, that's fine and we can learn from those through our developed model of how the world works. Maybe part of our brain's function is to explore what has not been tried every now and then to define our vision of the world. Data mining concepts do this on large databases.

Share this comment

Link to comment
Data mining concepts do this on large databases.

okay...it´s official....your a tease...your holding out on us. :D

I have to ask...do you have some links to these concepts ? or names of these concepts ?

Share this comment

Link to comment
LOL Michael, sorry I don't have a link. And I'm no expert on data mining (yet.. LOL). But I have a book that isn't the greatest, but it does have some good things on the subject especially on classification.

"Data Mining - Concepts and Techniques," Jiawei Han and Micheline Kamber, Academic Press, 2001.

Just so there's a little less confusion, what I meant was that the data mining ideas explore the large database every now and then to develop new relations instead of staying static. Since the database is large and dynamic, it's not practical to compute everything all at once.

Share this comment

Link to comment

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
  • Advertisement

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

GameDev.net is your game development community. Create an account for your GameDev Portfolio and participate in the largest developer community in the games industry.

Sign me up!