Is it true atom space objects are coded in functional languages? If so,
why?
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to opencog+unsubscr...@googlegroups.com.
It is my understanding that nn have gotten to the point where they can
generate a narrative from video input. I assume they could also use audio
input. With a nice slow text stream that can be memorized, as the data
volume is small, we can test programs to store important parts, react to
Does anybody know if there is a AGI 2018 conference?
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to opencog+unsubscr...@googlegroups.com.
To post to this group,
Can anyone point me to a discussion of applying neural networks to DNA
data?
I would like to see generative neural networks applied to DNA versus the
physical shape of the resulting animal.
Likewise for DNA versus IQ in humans. To answer what DNA is likely to give
IQ 300?
--
You received
My point is, Opencog is a set of functionality that one can use to build
higher level functionality. I am hoping Opencog will begin to accumulating
higher level solutions/functions.
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe
JanusGraph is just a graph store. It has no available reasoners.
It is best developed for Java and is weak for Python. As far as I can tell
there is no QA process.
JanusGraph is developed largely by IBM and Google as a replacement for
Titan which has been taken proprietary.
IBM would
There is lots of code. The wiki and the github contain all sorts of great
ideas.
Are there artifacts at the end level up? Is there an ontology? Software to
build an ontology from reading books?
Community AGI is a superb idea.
--
You received this message because you are subscribed to the
Thanks Linas, that works.
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to opencog+unsubscr...@googlegroups.com.
To post to this group, send email to
Is there an example of text input and rule output from the relex2logic ?
Thanks.
On Sunday, July 30, 2017 at 8:37:37 PM UTC-4, Ed Pell wrote:
>
> opencog/src/opencog/nlp/relex2logic
>
> ah I have it
>
> On Sunday, July 30, 2017 at 8:32:56 PM UTC-4, Ed Pell wrote:
>
opencog/src/opencog/nlp/relex2logic
ah I have it
On Sunday, July 30, 2017 at 8:32:56 PM UTC-4, Ed Pell wrote:
>
>
> Linas, sorry for the stumbling about question, where can I find the
> ""relex2logic" rules, which convert natural language to logic expressions"
Linas, sorry for the stumbling about question, where can I find the
""relex2logic" rules, which convert natural language to logic expressions"?
Thanks.
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop
Hi, I have tons of stuff installed and working. I have read various books
and papers. What I need now is a manual of a few major commands I can build
a guile(?) function from. Better yet some significant programs say one that
loads a "big" knowledge base and can answer question over the KB. Or,
Very nice. Seems like the most thorough parser I have seen. Is there a
co-reference resolver you know of? I have been doing some machine reading
of Wikipedia articles.
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this
Yes! I love it when people give definite answers.
So, just to check, the preferred language is Scheme?
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to
Check out Wave Computing Corporation and Graphcore Corporation both have
want you want.
>
>
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to
I am impressed with OWL2 and its support of spatial and temporal knowledge.
HermiT seems to support reasoning over these. What features will you be
adding?
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop
Linas, thanks for your thoughtful reply. Yes, the track record is spotty. I
also think that even if a whole system is written it will show/require
hardware acceleration for the memory. That is a hardware based associative
memory. That will allow mulling over big chucks of the memory in a
Thanks Mark.
On Friday, December 2, 2016 at 8:36:06 PM UTC-5, Mark Nuzzolilo wrote:
>
> I recommend: http://www.agiri.org/email/
>
>
>
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from
I too "I'm still frustrated that the overall system is still somehow too
complex for newcomers to be able to participate in it."
Ed
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it,
I hope you guys are filing patents or public disclosure on EVERYTHING.
Ed
On Sunday, November 20, 2016 at 11:24:24 AM UTC-5, Ben Goertzel wrote:
>
> I added a lot more detail to the "Link parse to logic via Lojban" page ...
>
> http://wiki.opencog.org/w/Link_Parse_to_Logic_via_Lojban
>
>
Linas, wonderful step forward. It is so pleasing to see the small surgical
team ahead of the massive corporate armies. Keep running the wolf packs
will get organized eventually. The more you put in the public domain the
less they can enclose and control.
Ed
On Sunday, November 20, 2016 at
The state of git-hub seems much improved. Now it is >=14 Ubuntu much better
than a specific version. I can clone everything. I have Moses installed! I
can cmake and make almost everywhere. The make test seems a bit weak? Still
working on this download.
It would be nice to have a checker tool
Noah, All, evolution gives humans and other living things many pre-canned
functions like edge detectors in the eye. In vision system some people add
the early edge detectors and some ask the blank slate to figure everything
out for itself from scratch. My preference is to give the system as
Linas, I would added a third model other. The three would be self, world,
other. Where "other" my have two versions a generic other (person) and many
copies of specific other (Alice, Bob, ...). Yes, other could be part of the
world model but it feels special enough to me to have its own
Linas, documentation is even better than raw code for disseminating
ideas/information in open source projects. Your document is much
appreciated.
I am happy to see someone talking about models of the world and self.
I am also happy to see documentation that is less mathematics based and
A company Deephi Techis offering a FPGA/memory chip on a board that could
be used for fast searches of text based db. http://www.deephi.com/en/
On Thursday, August 25, 2016 at 11:27:06 PM UTC-4, linas wrote:
>
> Hi Ed,
>
> Yeah, well, there is opencog (cog prime??) the abstract architecture, and
26 matches
Mail list logo