[ACT-R-users] ACTR, Semantic networks and declarative memory (UNCLASSIFIED)

[Kelley, Troy (Civ,ARL/HRED)]

Classification:  UNCLASSIFIED 
Caveats: NONE

Stuart,

Actually, we have just completed some work integrating ConceptNet into our
architecture which is SS-RICS, which is based on ACT-R, but is for robot
control.

As of right now we can execute a production in SS-RICS that will query the
ConceptNet database and return declarative memory chunks depending on your
assertion.  So you can say something like Hammers LocationOf - which is
basically a request to find where you are likely to find hammers, and a
fact, of type concept, will be created with Hammer and LocationOf ToolBox as
a slot.  So you would know that hammers are found in tool boxes.

We have worked hard to convert the ConceptNet database into something that
is more "accessible" than what was originally provided by the Python
interface.  We have converted the database to SQL Server and that has helped
tremendously.

Hopefully we will publish something this year. 

Cheers,
Troy D. Kelley
RDRL-HRS-EA
U.S. Army Research Laboratory
Human Research and Engineering Directorate (HRED)
Aberdeen Proving Ground, Aberdeen MD 21005-5425
voice: 410-278-5869
fax: 410-278-9523

-----Original Message-----
From: Stu @ AGS TechNet [mailto:stu at agstechnet.com] 
Sent: Tuesday, October 13, 2009 9:40 AM
To: Kelley, Troy (Civ,ARL/HRED)
Subject: ACTR, Semantic networks and declarative memory

Hello,
    I work with Dr Jerry Ball (and others), AFRL, Mesa AZ. I saw your post
on the ACT-R mailing list and I wanted to know how you finally resolved your
objective of leveraging existing semantic networks in ACT-R.  Did you
publish or present anything that you could share?
    
    Our team (AFRL, CERI, L-3, AGS TechNet) is currently building a domain
specific situation model for an aviation-related task and I would like to
leverage any successful approaches that offer facilities that might help.

Thank you for your time!
Stuart Rodgers

On 6/24/08 1:25 PM, "Kelley, Troy (Civ,ARL/HRED)" <tkelley at arl.army.mil
<http://act-r.psy.cmu.edu/mailman/listinfo/act-r-users> > wrote: >
Classification: UNCLASSIFIED > Caveats: NONE > > Susan, > > We have been
looking at using a semantic network as a starting point > for declarative
memory chunks. There are two major semantic networks that > we are looking
at using. ConceptNet from MIT and OpenCYC which is a spin > off of Doug
Lenat's work at the University of Texas. We are still working > on exactly
how to interface a semantic network with declarative memory > chunks, but I
think the general idea has promise. We are also trying to use > a production
syntax so that the same general productions don't have to be > developed
over and over. Both of these ideas have promise but we are still > working
on the implementations. > > Troy D. Kelley > AMSRD-HR-SE > Army Research
Laboratory > Human Research and Engineering Directorate (HRED) > Aberdeen
Proving Ground, Aberdeen MD 21005-5425 > voice: 410-278-5869 > fax:
410-278-9523 >
-- 


AGS TechNet

P.O.Box 752384

Dayton, OH 45475-2384

937-903-0558  Voice

513-297-0880  Fax

stu at agstechnet.com <mailto:stu at agstechnet.com> 

www.agstechnet.com <http://www.agstechnet.com/> 

Classification:  UNCLASSIFIED 
Caveats: NONE

-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/x-pkcs7-signature
Size: 5223 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/act-r-users/attachments/20091014/04228883/attachment.bin>