"Andrey Gavrilov" <andr_gavriloov@[EMAIL PROTECTED]
> writes:
| "Ondra Zizka" <ondra@[EMAIL PROTECTED]
> wrote in
news:48218b33$1@[EMAIL PROTECTED]
| > ...
| > 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?
| > ...
| > Thanks,
| > Ondra Zizka
|
| ...
| See any information on
| my sites below.
|
| Andrey Gavrilov
| http://uclab.khu.ac.kr/avg
| http://ermak.cs.nstu.ru
| http://www.insycom.ru
Thank you for the tips - based on that, I've found what I was looking
for. One of the first do***ent's I've found is
http://www.mind-consciousness-language.com/gavrilov%20principles.pdf
There you formulate "the training principle":
"When interacting with the environment, the intelligent system
stores the associations between different images which it uses to
plan and execute its behavior..."
That is exactly what I meant that "fuzzy graph-like database of
n-tuples" would be for - it would store those associations. See my
reply to Dmitry's post.
I have some idea of a system which would combine functional
programming, evolution algorithms, neural networks, genetic algorithms
and multi-agent systems; neural networks and evolution algorithms
would be its special cases. But, it's not time for me to develop some
theories until I read what's already done in this field.
Thanks again.
Ondra Zizka
[ comp.ai is moderated ... your article may take a while to appear. ]
|
