Re: Holistic World and Complexity

Ricardo Ribeiro Gudwin (gudwin@DCA.FEE.UNICAMP.BR)
Wed, 26 Aug 1998 10:43:47 -0300


Don Mikulecky wrote:

> neural networks and genetic algorithms are NOT mechanistic in the language we
> have
> so carefully developed. ANYTHING algorithmic is mechanistic (capable of
being
> computed by a universal Turing machine in the spirit of Church's thesis)

Don, I became curious here ... you said that NN's and GA's are NOT mechanistic,
and that ANYTHING algorithmic is mechanistic. But NN's and GA's are a type of
algorithms (in fact GA = genetic ALGORITHM) ! A possible difference is that
they are SELF-MODIFYING ALGORITHMS.
So, in this sense such SELF-MODIFYING ALGORITHMS are complex ?
Or do you just made a typo (... NOT non-mechanistic ...) ?
Regards,
Ricardo

--
                                                   //\\\
                                                   (o o)
 +-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-oOO--(_)--OOo-=-=-+
 \                   Prof. Ricardo Ribeiro Gudwin                /
 /             Intelligent Systems Development Group             \
 \    DCA - FEEC - UNICAMP    |           INTERNET               /
 /     Caixa Postal 6101      |     gudwin@dca.fee.unicamp.br    \
 \   13081-970 Campinas, SP   |       gudwin@fee.unicamp.br      /
 /          BRAZIL            |      gudwin@correionet.com.br    \
 +-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-+
 \ URL:        http://www.dca.fee.unicamp.br/~gudwin/            /
 / Telephones: +55 (19) 788-3819 DCA/Unicamp (University)        \
 \             +55 (19) 254-0184 Residencia  (Home)              /
 / FAX:        +55 (19) 289-1395                                 \
 +-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-+