[Techtalk] Prolog compilers, neural nets (was: Running Matlab & Nural Networking (Re: Remote X applications )

Sue Stones suzo at spin.net.au
Wed Mar 17 18:43:27 EST 2004


On Wed, 17 Mar 2004 02:19 pm, David Cohen wrote:
> As far as getting a Prolog system to work with, right now, the freebie that
> people are using appears to be SWI-Prolog, for which binaries are available
> for Windows, Mac and Linux:
>
> http://www.swi-prolog.org
>
> There's an IDE available too, called XPCE--look on the site and you'll see
> it.

I will certainly look into these even if I don't use prolog for neural nets

> Now, as far as doing neural nets with Prolog, I have to say the idea sounds
> a bit dodgy for the simple reason that the two approaches, logic and neural
> net, were typically viewed back in the heyday of commercial AI as being at
> odds with each other--the rule-based approach that attempts to mimic
> reasoning vs. the mindless numerical/statistical approach. Unlike some
> applications, I don't see any advantage that Prolog would give you here.

Hmm, definatly something to think about.

> Mind you, if you want to work with this type of high-level language, Common
> Lisp has excellent numerical facilities, as this discussion between Richard
> O'Keefe (a Prolog legend) and Daniel Lakeland
> mentions:
> http://www.swi.psy.uva.nl/projects/SWI-Prolog/mailinglist/archive/old/2389.
>html

Perhaps Lisp would be worth investigating.  Do you think Lisp is suitable for 
Neural nets?

> Hope this helps.

It most certainly gives me something to think about, and stops me getting over 
excited about the idea of using prolog.

sue


More information about the Techtalk mailing list