Return to the archive index

RE: rememberance agents

Yes, you can enter in new information by typing in sentences, and they'll be
written to a new file.

> -----Original Message-----
> From: R. Paul McCarty [mailto:]
> Sent: Sunday, April 26, 1998 12:09 PM
> To: Jesse Montrose
> Cc: 
> Subject: RE: rememberance agents
>
>
> I am compiling the ThoughtTreasure Talk package now, and it looks like
> exactly what I was looking for, but it doesn't appear to have an easy way
> to add new knowledge to the database by just typing in sentences (although
> there appears to be a story reading and understanding module which might
> be able to do the same).  If it isn't included, it probably wont be too
> much trouble adding a simple script that parses my sentences and
> reformats them in the format used by ThoughtTreasure.
>
> On Sun, 26 Apr 1998, Jesse Montrose wrote:
>
> > I've had some interest in this area myself, I would enjoy
> hearing about your
> > progress.
> >
> >
> >
http://wearables.www.media.mit.edu/projects/wearables/augmented-memory.html
> I assume you've looked at this one, right?

yes, I made sure to look at this before I asked any questions, but it
wasn't exactly what I was thinking of for a rememberance agent.

> Neural Networks can be built to run just fine on a 486, and you might find
> the processing done in the savant portion of project above to be a good
> place to start if you want to take that route.

maybe a small network would work okay on a 486 (say under 100 nodes), but
I can't imagine a network which can read sentences and answer questions
being anywhere near this size. :) I'm sure no one has even managed to
create such an AI with even the most powerful research computers.

> http://www.signiform.com/tt/htm/talk.htm
> This project is absolutely fascinating, but has resource requirements that
> will put it out of your wearable reach.  I recommend looking at it anyway,
c
> source code is available and you may find inspiration.  It also might work
> out for you to run TT on a more powerful machine, process your text files,
> and store the results on your wearable for easy lookup.  Here is an
excerpt
> from a sample of its "chatterbot mode" (all these answers come from TT's
> knowledge base):

yes, this is one very ambitious little program.

Are you using it right now? or did you just know about it.

Okay, its running now, doesn't seem too processor intensive in chat mode
on my pentium 166.  Now all I have to do is have it read a few general
computing FAQs, and pipe it all my email to answer. 8-)

aw, how cute, his name is Thomas.

-Paul

R. Paul McCarty / DARS Coordinator /  / x52059
317 Lattimore Hall, University of Rochester, Rochester, NY 14627
Computers don't make mistakes;what they do,they do on purpose.-Dale/KOTH

From Wear-Hard Mailing list Archive (WH)
Maintained by R. Paul McCarty

Archive created with babymail