h a l f b a k e r yNormal isn't your first language, is it?
add, search, annotate, link, view, overview, recent, by name, random
news, help, about, links, report a problem
browse anonymously,
or get an account
and write.
register,
|
|
|
Please log in.
Before you can vote, you need to register.
Please log in or create an account.
|
Generate a generalized way to encapsulate "knowledge" or "rules" which could then be use to create AI systems. Since it would be standardized, every app which created new "knowledge" could contribute to the whole "knowledge" bank
Useful for AI bots which might traverse the net and exchange info
with one another.
KQML
http://www.cs.umbc.edu/kqml/
It's been done (though not in XML). [egnor, Mar 14 2000, last modified Oct 17 2004]
FLBC
http://www.oasis-open.org/cover/flbc.html
Like KQML, but XML-based. [egnor, Mar 14 2000, last modified Oct 17 2004]
KIF
http://agents.umbc.edu/kse/kif/
another non-XML-based K-rep interchange system [big_lunk, Mar 14 2000, last modified Oct 17 2004]
DARPA Agent Markup Language
http://www.daml.org/
Blah blah ontology blah blah semantic web blah! [egnor, Mar 14 2000, last modified Oct 17 2004]
Artificial Intelligence Markup Language
http://www.alicebot.org/alice/aiml.html
Where "Artificial Intelligence" means "template patterned response", like Eliza or Ask Jeeves. [egnor, Mar 14 2000, last modified Oct 17 2004]
RDF
http://www.w3.org/RDF
[egnor, Oct 17 2004]
Digital mind modeling project
http://www.mindpixel.com
The ultimate knowledge bank in simple natural language [Xen, Oct 17 2004]
[link]
|
| |
I swear, when I first heard about XML I figured that's exactly what it was for. Since then, I've discovered that it's nothing more than dumb go-between language and I've been complaining about it ever since. |
|
| |
<DOGS>Snoopy, Lassie, Dyno-Mutt</DOGS>
<ANGST>small dick</ANGST>
<MAGICAL_HOUSECAT>Pyewackett;</MAGICAL_HOUSECAT> |
|
| |
So-frikkin'-what. Thing still has no idea of the importance of a magical housecat or Dyno-Mutt's relation to the Blue Falcon. |
|
| |
Both XML and AI rule systems generally fail to capture the complexity of meanings in human language; they have potential, but no built-in depth. Hence, they make fine bedfellows (as seen in the links); it's between either of them and humans that the system fails. |
|
| |
Yeah, and worse - some people's definition of intelligence hinges on whether you know how to pronounce "gnocchi" correctly or not. |
|
| |
"Luckily", the expert system shell vendors are for the most part all but dead. |
|
| |
The standards so far -- AIML aside, which isn't really a standard -- intentionally try to avoid specifying anything about the "type of logic used" or any other characteristic of reasoning. They're mostly about "declaring facts" and "representing knowledge", whatever that means to you. |
|
| |
if the ai was smart enough, they would just email each other. |
|
| |
and [triptych] see: all techno futuristic films/books. |
|
| |
Machines will learn how to reproduce, enslave mankind and take over the world!! |
|
| |