Hello,
I am a student of IT science caught by the AI and willing for more
knowledge. I hope I'll find some soulmates here.
I have learned about most types of neural networks, fuzzy systems, prolog
& lisp, functional programming, genetic algorithms, evolutionary
programming, etc.
But all of it seems to be just "inspired" by the nature, and is based on
mathematical models. Most of them has very narrow spectrum of problems it
can solve, compared to what AI is going to achieve as it's final goal (?)
- universal pondering, cogitating system.
I'm not going to ask dumb questions like "how big the NN should be to
learn it think" and such. My question is:
Is there some AI theory ( or idea / area of research aiming to create a
theory) which would cover most currently known concepts and use them
together?
What about some fuzzy graph-like database of n-tuples holding all
knowledge of an intelligent system, perhaps using neural networks to
create the fuzzy relations and to perform tranformations of both
short-term knowledge (aka. cogitation) and long-term knowledge (learning,
memorizing, creating memories) ?
Is there some such research?
I accept any references; I have a partial access to Springer, IEEE, and
such.
It may be a frequent question, but in the flood of information trash all
over the internet, I was not able to find something valuable.
Thanks,
Ondra Zizka
[ comp.ai is moderated ... your article may take a while to appear. ]
|
