Neural Nets learning by experience in runtime?

TriKri · 2006-06-04T02:55:21

If you where to create a neural network, starting from zero, with random initiated structure and random initiated weights, could you somehow do one long simulation of the network and get it to learn in runtime? Like the human brain, it must never be turned of. Still, the brain is learning. I supose it is not by back propagation, cause it does not know the right answear (BP otherwise, actualy would work on neural nets in runtime supposed it is feeded with the right answears). Does anyone know how to make a neural network learn without having the right answears? Or without having to make a change in the entire network, hoping to find out whether it was a good change or a bad change? Is there some way to, more like how the brain works I guess, make the network 'understand' whether a change would be profitable or what changes would be profitable? (This is probably one of the great mysteries of the brain, but I am hoping we are going to solve it here!) [Edited by - TriKri on April 29, 2006 6:49:45 PM]

Artificial Intelligence Programming

Started by TriKri April 27, 2006 05:19 PM

22 comments, last by Sagar_Indurkhya 18 years, 5 months ago

Sagar_Indurkhya

253

May 27, 2006 12:21 PM

Cheah! I won 3rd Place at the Intel International Science and Engineering Fair with that project!

Anyway, I'm taking a month or two off to think about the project. A couple problems I see:

1) It takes a very very very veyr very long time to get this to work. Granted, I was doing research with no aim to make it for a feasible game, so I had massive networks to see how far I could get.

2) I still don't fully understand the constraints required for the environment for this to work. Do the bots need food? Should they be able to manipulate the environment? Should they try to reproduce or should I just automate that process for them randomly?

3) I'm very suspicious of the genetic algorithm method I use to train the Situation Analysis Network(which decides if something is good or bad), as either my population size isn't large enough or I'm not adequately covering the search space.

4) Once you get the bot intelligent, you can't really understand why it is intelligent. Then again, do we want to know why it's intelligent as long as it is? etc.

Consequently I'm shifting my focus to the mathematics of complex adaptive systems. I'm hoping this will give me a better understanding of how to study the architecture of the brain.

My Wiki

tthibault

100

May 30, 2006 09:18 AM

Quote:
check out NERO (neuro evolving robotic operatives) that uses NEAT
and
http://www.cs.ucf.edu/~kstanley/

have phun :D

Marty

Is that the same guy at AI-Junkie.com, a lot of the more basic code seems to be the same.

Quote:
Cheah! I won 3rd Place at the Intel International Science and Engineering Fair with that project!

Sweet, that's pretty cool, good job! I'm very interested in you posting your work

Good thread, helping me a bunch.

...and do not wildly extrapolate. Just because Saddam Hussein gassed Kurds in 1990 doesn't mean he eats babies' brains.

Anonymous

June 04, 2006 02:54 AM

Quote: Original post by tthibault
Quote:
check out NERO (neuro evolving robotic operatives) that uses NEAT
and
http://www.cs.ucf.edu/~kstanley/

have phun :D

Marty

Is that the same guy at AI-Junkie.com, a lot of the more basic code seems to be the same.

Quote:
Cheah! I won 3rd Place at the Intel International Science and Engineering Fair with that project!

Sweet, that's pretty cool, good job! I'm very interested in you posting your work

Good thread, helping me a bunch.

Yep, $4,000 cash too! I'm recoding the project in Mathematica right now, as I think Mathematica will give me a better way to analyze my results. I'm hoping to publish soon.