Lotfi Zadeh: A New Frontier in Computation – Computation with Information Described in Natural Language

I have one other notes of WCCI conference. It is about an invited talk by Lotfi Zadeh, the father of Fuzzy logic. I do not know whether this post would be useful to anyone or not, because I do not try to make my notes into a readable text, e.g. sometimes I just wrote a word or phrase as a reminder for myself. However, it may act the same and give you some hints to something useful!

Monday (17 July 2006) – 5:25PM
Now, I am going to attend Lotfi Zadeh’s invited talk. He is the father of Fuzzy logic. I haven’t seen him before, so I am a bit excited. This confrontation is specially important for me because I highly respect his idea (some kind of idol for me!).
Let’s see what he will talk about. The title of the talk is “A New Frontier in Computation – Computation with Information Described in Natural Language”.

-He mentioned that one big problem in current AI research is the lack of attention to the problem of perception. He thinks that without solving this problem, we cannot reach human-level intelligent machines.

Natural Language as a way of perception. It is not addressed that much in AI community.

(What is generalized constraint-based systems?! [My question to myself. He address it later.])

Well …
Fundamental Thesis:
-Information = generalized constraint
-Proposition is a a carrier of information

Meaning Postulate:
-Proposition = generalized constraint

Computation with Words!

Quotation:
“Fuzzy logic” is not fuzzy logic.
Fuzzy logic is a precise logic of imprecision.

Granulation is a key concept!
There is no concept granulation in probability theory.

What is the maximum value of a curve that is drawn by spray pen?!

Precisiation!

(Is there anything like Fuzzy SVM or Fuzzy Margin Maximization?! Fuzzy Margins?! [My question to myself])

Precisiation and Imprecisiation
Humans have tolerance to imprecisiation

Fuzzy logic deals with summarization.

Cointensive:
There are many definitions (e.g. stability, causality, relevance, mountain, risk, linearity, risk, cluster, stationary) that are not cointensive. There is not a 0/1 concept of stability. These are fuzzy concepts. [Well! I like this idea!]

“Generalized Constraint Language”

Leave a Reply

Your email address will not be published. Required fields are marked *