On Feb 7, 2008 9:05 PM, Jakub Kotowski <jakubkotowski@xxxxxxx> wrote:
>
> > I don't know how chaos is regarded in information theory.
>
> I unfortunately do not have much background in information or chaos
> theory but I am interested in it too. I googled a paper that may be of
> interest to you because except chaos and information theory it also
> refers to Kolmogorov's algorithmic complexity (algorithmic entropy).
> However, they are more concerned with measuring information and entropy
> of finite strings (with a possible application to data compression):
> Deterministic Chaos and Information Theory (Mark R. Titchener, Werner
> Ebeling):
> http://tcode.tcs.auckland.ac.nz/~corpus/DCC2001.ps (01)
Thanks for this paper. (02)
> > I'm backing into all of this from the kinds of patterns we see when we
> > try to learn classes from flat text.
> What kind of patterns you mean? (03)
Contradictory and random ones. (04)
The most successful modern language models are statistical. (05)
If you look for it, you can find suggestions that language classes are
non-linear going back to the '60 or earlier, but these were broadly
ignored. Much of linguistics completely abandoned the study of
structure instead (the other half assumed structure was innate, and
observable structure irrelevant.) (06)
-Rob (07)
_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
Subscribe/Config: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/
To Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx (08)
|