Re: [opencog-dev] Re: Running the pattern miner

<opencog@googlegroups.com> wrote: > Apparently this branch was started a year ago. > > Shujing, what prevents you from merging it into the master? > > Nil > > > On 06/29/2016 10:45 AM, Ben Goertzel wrote: >> >> True... though I wonder what incompatibilities

[opencog-dev] Re: An unsupervised learning with pattern mining demo

kek...@gmail.com> wrote: > To anyone who has interest, > > I just finished a new demo for unsupervised learning from observations with > pattern mining. > > https://www.youtube.com/watch?v=X8C7nhIULZs > > Best, > Shujing -- Ben Goertzel, PhD http://goertzel.org Su

[opencog-dev] Language learning from simple robot head experience

tter visual perception for their robots, and as this becomes a reality we will be able to use it within the above process.. -- Ben Goertzel, PhD http://goertzel.org Super-benevolent super-intelligence is the thought the Global Brain is currently struggling to form... -- You received this mes

Re: [opencog-dev] Re: Language learning from simple robot head experience

> AGI is essential for them. Opecog is the only complete approach to reach it. > Is there nobody at Google who watch closely opencog -and- understand what it > is doing? > > Respect! > Andi > > > > > > Am Freitag, 29. Juli 2016 03:32:11 UTC+2 schrieb Ben Goer

Re: [opencog-dev] goertzel.org seems not to be online?

/www.mcafee.com/threat-intelligence/site/default.aspx?url=http://successurls.org/bssIn?extra_param_1=G91825=_source=wp.goertzel.org_medium=redirect_campaign=general_content=general_term=Ben%20Goertzel%27s%20Website > > > Am Dienstag, 2. August 2016 14:59:19 UTC+2 schrieb Ben Goertzel:

[opencog-dev] Re: [hansonrobotics/HEAD] ROS NMPT Salience Detector: Degree Values and Salient Feature Tracking (#117)

t swing out > of your way when you approach them were were in all the supermarkets by the > 1960's -- turning your head to look at something "salient" is at about the > same level of sophistication. Its been 50 years. Yes, get to that, but then > go farther. > > -

Re: [opencog-dev] Re: brainstorming new names for OpenCogPrime

e: everybody in the scene will remenber this name and what it means > and who made the design and with what tools it was made - the opencog > toolset. > > In this way the first gift from BensSanta will be that more people know > about and remember opencog... > > Andi > >

Re: [opencog-dev] What CYC has done wrong

oups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/CAHrUA369vqLVG7xEx5vVS%2BASqtaKMNSVBc7S3rdxdU8gGgEFOQ%40mail.gmail.com. > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertze

Re: [opencog-dev] Re: OpenCV for preliminary visual processing?

olent > predators, crazy forest shit. Its hard to imagine how to get that > kind of a sonically-rich environment for a robot, unless you put the > robot in a back-pack and went hiking around in the city or country or > wherever. > > Or tapped into the mics on 1 million cellphones... yo

[opencog-dev] Soliciting GSoC 2017 ideas

page here and added some stuff to it, http://wiki.opencog.org/w/Early_2017_Ideas_Page -- feel free to add your own stuff, the deadline is Feb 8 ... thanks ben -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed,

Re: [opencog-dev] Setting Goals and Actions as OpenPsi Rules

the web visit > https://groups.google.com/d/msgid/opencog/8f34f57e-5c67-459b-9c09-74de4cb5a00b%40googlegroups.com. > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is he

[opencog-dev] Re: Pattern Miner improvements

should be like, I will have > a look at it and evaluate how much work it will be and if I have time to do > it. > > Thanks, > Shujing > > > On Fri, Feb 10, 2017 at 12:34 PM, Ben Goertzel <b...@goertzel.org> wrote: >> >> Nil, >> >> We have about 8

[opencog-dev] Re: Pattern Miner improvements

Hi Nil, > I'm not familiar enough with the pattern matcher yet to suggest a Scheme > API. I do believe I know however the next steps to clean it up. So I'll look > into that first, create a github issue, then look into the API design. Thanks, that will be helpful! > In fact for the API, it

[opencog-dev] Tensorflow Fold, unsupervised learning on graphs/trees, etc.

.. -- Ben -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed, so you can go in the opposite direction. Don’t polish the brass on the bandwagon.” – V. S. Ramachandran -- You received this message because you are

Re: [opencog-dev] how to best think of the 'confidence' in simple truth value

egroups.com?utm_medium=email_source=footer>. >>> >>> For more options, visit https://groups.google.com/d/optout. > > > -- > You received this message because you are subscribed to the Google Groups > "opencog" group. > To unsubscribe from this grou

Re: [opencog-dev] questions around the eva-chatbot, and current state of the opencog-nlp pipeline

rain's a little washed out :) > > Anyways, let me know... > > > On Saturday, January 14, 2017 at 10:49:22 PM UTC-5, Ben Goertzel wrote: >> >> Hi, >> >> > - Is "Relex2Logic" is still an actively used step in the opencog<->nlp >> >

Re: [opencog-dev] Re: [Link Grammar] Re: probabilistic type theory with records ... variants of categorial grammar & semantics, etc.

On Sat, Sep 3, 2016 at 9:59 AM, Linas Vepstas wrote: > Hi Nil, > >> >>> >>> These same ideas should generalize to PLN: although PLN is itself a >>> probabilistic logic, and I do not advocate changing that, the actual >>> chaining process, the proof process of arriving at

Re: [opencog-dev] Re: [Link Grammar] Re: probabilistic type theory with records ... variants of categorial grammar & semantics, etc.

ntextAnchorNode "123" EmbeddedTruthValueLink <0> ContextAnchorNode "123" Inheritance Ben sane which uses more memory but does not complicate the core code so much... -- Ben -- Ben Goertzel, PhD http://goertzel.org Super-benevolent super-intelligen

Re: [opencog-dev] Re: [Link Grammar] Re: probabilistic type theory with records ... variants of categorial grammar & semantics, etc.

would expect surface syntax to emerge via multiple constraints include -- ease of tweakability into deep structures that parallel semantic structure -- ease of comprehension and production of surface structure I believe Jackendoff made this latter point a few times... -- Ben On Sat, Sep 3, 201

Re: [opencog-dev] Re: [Link Grammar] Re: probabilistic type theory with records ... variants of categorial grammar & semantics, etc.

> MAPPING SYNTAX TO LOGIC > > "RelEx + RelEx2Logic” maps syntactic structures into logical > structures. It takes in structures that care about left vs. right, > and outputs symmetric structures that don’t care about left vs. right. > The output of this semantic mapping framework, given a

[opencog-dev] Fwd: [open-nars] credit assignment

It would be Interesting to compare PLN with NARS on these simple credit assignment ish examples -- Forwarded message -- From: "Pei Wang" Date: Sep 5, 2016 2:59 AM Subject: [open-nars] credit assignment To: "open-nars" Cc:

[opencog-dev] probabilistic type theory with records ... variants of categorial grammar & semantics, etc.

of finite-dimensional vector spaces This approach accepts fundamental heterogeneity in semantic representation... -- Ben -- Ben Goertzel, PhD http://goertzel.org Super-benevolent super-intelligence is the thought the Global Brain is currently struggling to form... -- You received this message

Re: [opencog-dev] Re: [Link Grammar] Re: probabilistic type theory with records ... variants of categorial grammar & semantics, etc.

ng is a category error: the logic that describes >> parsing is not PLN, and PLN dos not describe parsing: its a category error >> to intermix the two. >> >> Phew. >> >> What remains to be done: I believe that what I describe above, the >> "many-worlds

Re: [opencog-dev] Pattern Miner and missing libTestPatternMinerAgent.so

isit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/e49d87f5-565d-4e94-9e28-ef3380b254b2%40googlegroups.com. > > For more options, visit https://groups.google.com/d/optout. -- Ben

Re: [opencog-dev] Re: opencog with crawled data

hanks in advance > > > -- > 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

Re: [opencog-dev] Re: Fringe of consciousness, importance spreading

On Tue, Sep 13, 2016 at 12:49 AM, Roman Treutlein <lordmor...@gmail.com> wrote: > Do you just spread it from your Source to it's Targets and then use these > Targets as a new source? yah, that was my thinking... not too fancy but I don't see what else to do... -- Ben Goertz

Re: [opencog-dev] Fringe of consciousness, importance spreading

ralized version of AF >spreading rather than a new method. As Roman points out, the actual mechanics >of how to spread K links out also needs to be determined. > > —matt > >> On Sep 12, 2016, at 10:01 AM, Ben Goertzel <b...@goertzel.org> wrote: >> >> A somewh

Re: [opencog-dev] Fringe of consciousness, importance spreading

e default setting for K would be one but that >> this would change for specific contexts. >> >> On Sep 12, 2016, at 10:59 AM, Ben Goertzel <b...@goertzel.org> wrote: >> >> Rather than introduce a new third method, it seems to me that we could >> simply repla

Re: [opencog-dev] Re: Embodied Language

ttps://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/CAHrUA34MQdz7u4Gsuj4%2BmpPJj%2BhLu-NVX0gOZ0FrkwxHemNgVg%40mail.gmail.com. > > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD ht

[opencog-dev] Fringe of consciousness, importance spreading

et boosted into the AttentionalFocus -- Ben -- Ben Goertzel, PhD http://goertzel.org Super-benevolent super-intelligence is the thought the Global Brain is currently struggling to form... -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubsc

Re: [opencog-dev] OpenCV for preliminary visual processing?

system. It also has the advantage of being potentially faster to > implement and scale. > > I don't see this implementation ever being a replacement for any sort of 3d > map formation, but rather a low-overhead way of quickly making sense of raw > visual input without pumping r

Re: [opencog-dev] Re: ImplicationLink?

ely, that more explicit articulation of logical structures in Atomspace reduces confusion, and is thus worthwhile even when it makes things a bit less elegant... -- Ben Goertzel, PhD http://goertzel.org Super-benevolent super-intelligence is the thought the Global Brain is currently struggling to f

[opencog-dev] Cogistry: Accelerating Algorithmic Chemistry via Cognitive Synergy

... Not that we don't have enough work to do already... -- Ben Goertzel, PhD http://goertzel.org Super-benevolent super-intelligence is the thought the Global Brain is currently struggling to form... -- You received this message because you are subscribed to the Google Groups "opencog&q

[opencog-dev] Re: EvidenceCountTV

you mean, on an abstract level at > least. So let's put the requirement: whenever an reasoning rule can be > agnostic of the total count and some if its premises have undefined total > count, the rule should be able to propagate just the positive count. > > Do these 2 points above entir

[opencog-dev] EvidenceCountTV

hich can be derived from positive_evidence and total_evidence... Adding new TV types like this is annoying, but OTOH abusing the "strength" or "mean" field in an existing TV type by making it mean positive_evidence for certain link types, seems even more annoying... Hopefu

Re: [opencog-dev] symbolic grounding

To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/e3122cd7-7124-4a5c-8a0f-a089aef339b6%40googlegroups.com. > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertzel.org Super-benevolent super-intelligence is the t

Re: [opencog-dev] Making WordNode multi-lingual... ProtoAtom once again...

bother doing reasoning or attention allocation on this link This is not a huge point in the end, but it's one among many examples of the flexibility that would come from putting TV and AV in the Atomspace instead of having them as hard-coded structures... -- Ben On Tue, Nov 22, 2016 at 12:11 PM, Ben Goertzel

[opencog-dev] Making WordNode multi-lingual... ProtoAtom once again...

ProtoAtom implementation (not fundamentally hard to do, just tedious), which would allow us to have ProtoAtoms indicating "English" and "Chinese" etc. and link them from WordNodes to indicate the language they correspond to We should discuss moving forward on ProtoAtom duri

Re: [opencog-dev] Making WordNode multi-lingual... ProtoAtom once again...

rd. > > Finishing the protoatom work is not "tedious"; rather, there are a few > remaining important architectural issues that need to be decided on. They > are not simple decisions, they've got some strong pro& cons reprecussions, > which is why that work was deferred. They'r

Fwd: [opencog-dev] Variables, names, etc.

be changing the name for > everyone who is holding it, in every scope. You only want to change the > name in the local scope. > > --linas > > On Thu, Sep 3, 2015 at 8:11 PM, Ben Goertzel <b...@goertzel.org > <mailto:b...@goertzel.org>> wrote: > > That co

Re: [opencog-dev] Is automatic alpha-conversion evil?

problem doesn't arise. > > I'm re-iterating my question. Do we really want automatic alpha-conversion > to begin with? > > If the answer is yes then I suppose we need a way to tell that the quoted > version is different than then unquoted version. > > Nil > > > On 10/22/2016

Re: [opencog-dev] Re: Extract Alternative Sentences

On Fri, Nov 18, 2016 at 7:55 AM, Ben Goertzel <b...@goertzel.org> wrote: > I think I know how to use this to make a replacement for RelEx2Logic, > by using a parallel English-Lojban corpus, and then using the pattern > miner to find patterns from the set of pairs of the form &g

Re: [opencog-dev] how does the concepts of PLN fit into the opencog system

d join the initiative on the Hanson robotic head. I'm > just not sure where to start from... yet. > > Are there any planned remote interactive session(s) during the december > hackathon event, by any chance? > > On Saturday, November 12, 2016 at 4:54:27 PM UTC-5, Ben Goertzel

Re: [opencog-dev] How much longer?

p, send email to opencog@googlegroups.com. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/2691445b-d42d-4f66-9e2d-328a3a6a6188%40googlegroups.com. > For more options, visit https://gro

[opencog-dev] Link Parse to Logic via Lojban

y learning Linas is likely to work on next year, we can finally have all the large heaps of nasty doo-doo out of OpenCog ... and replaced with cool stuff ;) ... -- Ben -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is

Re: [opencog-dev] Trying to understand how solving TruthQuery works

a2d-4049-968f-8f7120f43e51") >> > (ConceptNode >> > "game@85e71213-577b-4aa2-8412-da49e62ba2f4") >> > ) >> >) >> > | >> > >> > >> > I apprecia

Re: [opencog-dev] Re: Link Parse to Logic via Lojban

tion and >> action based learning working a lot better than we do) ... >> >> With this plus the unsupervised link-grammar-dictionary learning Linas >> is likely to work on next year, we can finally have all the large >> heaps of nasty doo-doo out of OpenCog ... and replaced wi

[opencog-dev] Re: EvidenceCountTV

Hi Nil, > I'm trying to understand specifically your problem. By instances I suppose > you mean > > EvaluationLink (stv 1 1) > PredicateNode "eat_342" > List > ConceptNode "cat_132" > ConceptNode "mouse_243" > > for a positive one. > > Evaluation (stv 0 1) > PredicateNode "eat_635"

[opencog-dev] Hong Cogathon Dec 2016

We crazy Hong Konger OpenCog/Hansonites be at it again ... Nov 28-Dec 9 ... http://opencog.org/2016/10/hong-cog-a-thon-dec-2016/ http://wiki.opencog.org/w/Hong_Cogathon_Dec_2016 -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction

Re: [opencog-dev] Re: ImplicationLink?

gt;>> cannot >>> possibly >>> be right). >>> >>> I'm asking, because I'm trying to fix #910 by >>> doing the >>> alpha >>>

Re: [opencog-dev] Re: ImplicationLink?

ion >>> links in them now fail. The whole thing smells bad. >>> >>> Either ImplicationLinks do inherit from ScopeLink, in >>> which >>> case, there >>> should be no complaint

[opencog-dev] Generalizing the Pattern Miner implementation to make it encompass the MOSES algorithm

And then, as the Aussies say, Bob's your Uncle... ;) -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed, so you can go in the opposite direction. Don’t polish the brass on the bandwagon.” – V. S. Ramachandran -- You

[opencog-dev] Re: temporal reasoning

eis...@googlemail.com> wrote: > Good you mentioned, I wasn't aware of it. I suppose as soon as the BC works > well, tackling time server + temporal reasoning is gonna be the next step, > say in parallel to starting working on scalable inference control. > > Nil > > > On 12/

[opencog-dev] Re: Generalizing the Pattern Miner implementation to make it encompass the MOSES algorithm

Nil, > Interesting. So the way I see it is that you start from a general pattern T. > You find atoms that meet that pattern, based on these atoms you refine T > into T1, or perhaps rather an ensemble of T1s, right? > > You do need a scheme that defines how you go from T to T1 though, what is >

[opencog-dev] Soggy predicates

ConceptNode “cat” ConceptNode “mouse” SatisfyingSet ConceptNode “eat” which means that s is the average degree to which an observation (in the default overall observation-set) involving “eat”, also involves the pair (eater = cat, eatee=mouse). -- Ben Goertzel, PhD http://goertzel.org “I

[opencog-dev] Fwd: [mizar] PhD positions on the AI4REASON project in Prague

ption of your research accomplishments and interests, including the names of two references. Deadlines: March 1, 2017, or until the positions are filled. Earlier applications are welcome and and early start date is an advantage. -- Ben Goertzel, PhD http://goertzel.org “I tell my

Re: [opencog-dev] Super interesting paper from Fei-fei Li group tackles scene graph generation

legroups.com. > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed, so you can go in the opposite direction. Don’t polish the brass on the bandw

Re: [opencog-dev] Super interesting paper from Fei-fei Li group tackles scene graph generation

elopments of > unsupervised learning also. > GAN seems to be a promising approach in feature generation. Have you > considered to try? > > Yuhuang. > > On Saturday, January 14, 2017 at 4:44:42 PM UTC+1, Ben Goertzel wrote: >> >> Interesting. This approac

Re: [opencog-dev] inference trails

its worth understanding what kind of >> logic applies to the URE itself. I think Girard has a partial answer >> to this, unfortunately, its not written at an easy-to-grasp level. >> >> --linas >> >> >> >> On Sun, Jan 8, 2017 at 2:33 AM, Ben Goertzel <b..

[opencog-dev] abstract pattern matching

t there as something to consider if we ever want to pretty much rebuild the pattern matcher from the ground up ;p ... -- Ben -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed, so you can go in the opposite direction. Do

Re: [opencog-dev] Problems with opencog build - very low priority beginner question

HI, > The project is very, very interesting, but the start is very hard. I OpenCog > had be available as Windows or Java programs then every novice could be able > to run server, to create AtomSpaces, to start experiments, to use without > programming knowledge. But OK, I can continues in this

[opencog-dev] Thoughts on ECAN testing, weak links, etc.

here we should be able to move on to using ECAN to help provide guidance to PLN for common-sense inferences... -- Ben -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed, so you can go in the opposite direction. Don’t

[opencog-dev] OpenCog + OpenAssistant?

re working on an Android port now... one could also add a talking-head avatar... -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed, so you can go in the opposite direction. Don’t polish the brass on the bandwago

Re: [opencog-dev] OpenCog dev thru Nao

gle.com/d/msgid/opencog/2be7e1aa-e1e0-43f0-8bea-ccbafa04d417%40googlegroups.com. > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertzel.org “Our first mothers and fathers … were endowed with intelligence; they saw and instantly they could see far … the

Re: [opencog-dev] word2vec within openCog language learning?

On Mon, Mar 27, 2017 at 10:12 AM, Ben Goertzel <b...@goertzel.org> wrote: > Now, the distinction between word2vec and sense2vec may indeed be > relevant here, because a word may be meaningfully be placed into two > categories at this stage (i.e. word sense disambiguation). So we m

[opencog-dev] Pattern mining and NLP parsing and MOSES with the URE?

would be specified by a "pattern template" similar to what one uses in the pattern miner now to specify what kinds of patterns to search for... ... Doing 1-3 would make things rather elegant (and combined with our in-progress replacement of the NLP comprehension pipeline, would make the wh

Re: [opencog-dev] word2vec within openCog language learning?

his group, send email to opencog@googlegroups.com. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/CADwLDSTAwTGHninLdkiExtd-kePKdi_3q2W99OveqkPRo5b1bg%40mail.gmail.com. > > For more op

Re: [opencog-dev] word2vec within openCog language learning?

amples -- Ben On Mon, Mar 27, 2017 at 8:39 AM, Cassio Pennachin <pennac...@gmail.com> wrote: > Hi Ben & Linas, > > I assume you're familiar with sense2vec. At the one paragraph level of > detail, this suggestion seems pretty similar to me, any key differences? > > On Sun

[opencog-dev] word2vec within openCog language learning?

else in Addis could work on, I think... We can discuss at the office this week... ben -- Ben Goertzel, PhD http://goertzel.org “Our first mothers and fathers … were endowed with intelligence; they saw and instantly they could see far … they succeeded in knowing all that there is in the worl

[opencog-dev] news flash from OpenAI: evolution works!

In the "Well, duhhh" department -- OpenAI finds evolution distributed strategies outperform neural nets for reinforcement learning in test problems, https://blog.openai.com/evolution-strategies/ -- Ben Goertzel, PhD http://goertzel.org “Our first mothers and fathers … we

Re: [opencog-dev] word2vec within openCog language learning?

> On Mon, Mar 27, 2017 at 6:11 PM, Ben Goertzel <b...@goertzel.org> wrote: >> >> On Mon, Mar 27, 2017 at 10:12 AM, Ben Goertzel <b...@goertzel.org> wrote: >> > Now, the distinction between word2vec and sense2vec may indeed be >> > relevant here, because a

Re: [opencog-dev] How can we express modalities in OpenCog?

>> For more options, visit https://groups.google.com/d/optout. > > > -- > 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 > e

Re: [opencog-dev] How can we express modalities in OpenCog?

; > --linas > > On Wed, Mar 15, 2017 at 11:14 AM, Ben Goertzel <b...@goertzel.org> wrote: >> >> Code and theory for extending PLN to handle modal reasoning regarding >> beliefs, knowledge and so forth is here: >> >> >> https://github.com/sum

Re: [opencog-dev] How can we express modalities in OpenCog?

same as EvaluationLink Predicate "belief". Not only would a port > into the current PLN infratructure be useful, but that should be followed by > a tutorial/example, and there should also be a hookup into the chatbot. That > would ... make for a fun demo. > > > On Wed, Mar

Re: [opencog-dev] PLN rules selection

> The R2L code does have some fundamental design flaws: the rules are > hand-coded, there are about 60 or so of them, and we really need twice as > many, but even if we had more, they most they can deal with is relatively > unambiguous factual English sentences. What we really need is a way to >

Re: [opencog-dev] Merge SUMO_importer

Not really... though see the to do list ... On Apr 5, 2017 01:14, "'Nil Geisweiller' via opencog" < opencog@googlegroups.com> wrote: > Any reason > > https://github.com/tanksha/external-tools/tree/master/SUMO_importer > > hasn't been merged to > > https://github.com/opencog/external-tools > > ?

Re: [opencog-dev] Training data

to opencog+unsubscr...@googlegroups.com. > To post to this group, send email to opencog@googlegroups.com. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/894952b4-56e9-4438-a78a-edbac050f275%40googlegroup

Re: [opencog-dev] Re: word2vec within openCog language learning?

nclark609/talks > > > Warm regards, Jesus Lopez. > > > > On Sunday, 26 March 2017 18:44:10 UTC+2, Ben Goertzel wrote: >> >> Linas, >> >> I thought a bit about how to use a modified version of the word2vec >> idea in our language learning pipeline... &g

Re: [opencog-dev] Re: word2vec within openCog language learning?

Having thought a little more... I'll need to think more about what's the right network architecture to handle the inputs for applying the InfoGAN methodology to this case... On Wed, Apr 12, 2017 at 4:46 PM, Ben Goertzel <b...@goertzel.org> wrote: > Speculating a littl

Re: [opencog-dev] Re: word2vec within openCog language learning?

sentence syntax and have the local Markov > property. The factors are for words of complex syntactic cateogory (as > N/N...) and their attached tensors are multivariate conditional > probability distributions. > > Hope this helps somehow. Kind regards, > Jesus. > > > [1] http:/

[opencog-dev] Re: [Link Grammar] Algebraic view of word grammar...

n the order of sisters > (e.g. I gave the students high marks vs: *I gave high marks the students), > but it's not necessary, whereas they obviously have to be in some actual > order. (Sister constraints are an outstanding gap in the theory, I'm > afraid.) > Mutual dependenc

[opencog-dev] Algebraic view of word grammar...

by + operators) probabilistically weighted. But I'm out of time just now so that will be saved for later ;) ... ben -- Ben Goertzel, PhD http://goertzel.org "I am God! I am nothing, I'm play, I am freedom, I am life. I am the boundary, I am the peak." -- Alexander Scriabin -- Yo

Re: [opencog-dev] Re: word2vec within openCog language learning?

induction algorithm... ben On Wed, Apr 12, 2017 at 6:50 PM, Ben Goertzel <b...@goertzel.org> wrote: > Having thought a little more... I'll need to think more about what's > the right network architecture to handle the inputs for applying the > InfoGAN methodology to this case...

Re: [opencog-dev] Re: Best texbook (most relevant to Opencog Node and Link Types) in Knowledge representation

or Pei Wang's book a moment's search shows that it is easily downloadable from libgen if you want to read it... ben -- Ben Goertzel, PhD http://goertzel.org "I am God! I am nothing, I'm play, I am freedom, I am life. I am the boundary, I am the peak." -- Alexander Scriabin -- You recei

Re: [opencog-dev] Re: Best texbook (most relevant to Opencog Node and Link Types) in Knowledge representation

> > any thought would be much appreciated ... > > thank you, > > Daniel > > > > > > On Wednesday, 19 April 2017 09:16:42 UTC+3, Ben Goertzel wrote: >> >> We have a probabilistic logic engine (PLN) which works on (optionally >> probabilistically lab

Re: [opencog-dev] Re: OpenCog on Tizen?

nter to either a posted guide to successfully building >> OpenCog on the Raspberry Pi, or to a person who you know who has done this >> that would be willing to share a few details to be sure I don't make a mess >> of it. >> >> Thanks for your help, I hope to be able to c

Re: [opencog-dev] OpenCog Book / Manual

oglegroups.com. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/96cef80e-ba3e-c03c-2823-c217230048ac%40gmail.com. > > For more options, visit https://groups.google

Re: [opencog-dev] NLP - moving to Word grammar (are there tools?), understanding language, universal reference knowledge base

ad to something word grammar like in some ways... -- Ben Goertzel, PhD http://goertzel.org “Our first mothers and fathers … were endowed with intelligence; they saw and instantly they could see far … they succeeded in knowing all that there is in the world. When they looked, instantly they saw all a

[opencog-dev] Asymmetric attraction in unsupervised language learning

mar, and I suspect that having heads for the link is valuable... I also think that having directedness to links is going to be valuable for inferring abstract semantic relations from this statistical data, because directness gives you head-dependent relationships, which tend to translate int

Re: [opencog-dev] How can we express modalities in OpenCog? New types of nodes and links?

@googlegroups.com. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/7a0255ac-5d6c-41a8-aa7f-a967c9534381%40googlegroups.com. > For more options, visit https://groups.google.com/d/optout

[opencog-dev] learning morphological relations

reading should quell it even more given the nature of real-world sentences... Just wanted to get the contents of the discussion down in writing before it got too badly lost in my memory... -- Ben -- Ben Goertzel, PhD http://goertzel.org “Our first mothers and fathers … were endowed with intelli

Re: [opencog-dev] Re: Algebraic view of word grammar...

e > allowed in certain cases > you dont use classes/subclasses because you don't need them > > As for your weighted links... they don't fit anywhere :-) > > > On Wednesday, 5 April 2017 23:26:20 UTC+1, Ben Goertzel wrote: >> >> Some quasi-mathematical-linguist

Re: [opencog-dev] Re: Best texbook (most relevant to Opencog Node and Link Types) in Knowledge representation

isit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/a6d0102e-9ca1-4204-8dd4-75a9fb2ec06b%40googlegroups.com. > > For more options, visit https://groups.google.com/d/optout. -- Ben Goert

Re: [opencog-dev] Re: Best texbook (most relevant to Opencog Node and Link Types) in Knowledge representation

e learning is real-time experiential rather than batch-based but there's plenty of nitty-gritty work here... ben goertzel On Wed, Apr 19, 2017 at 7:23 AM, Daniel Gross <gross...@gmail.com> wrote: > Hi Linas, > > How do you propose to learn an ontology from the data -- also, what

Re: [opencog-dev] Java 8

> In the meanwhile, there is an effort is to create a scripting language that > will allow non-programmer artists to create scripted actions and reactions. > Unfortunately, this completely blows-off and ignores the concept of a > "middle form", and so there is no path forward from scripting to a

Re: [opencog-dev] Re: Chinese, English databases

email to opencog@googlegroups.com. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/393b88c8-aadd-456c-bd84-eaac92b55fd8%40googlegroups.com. > > For more options, visit https://groups.google.co

[opencog-dev] Re: Symmetric Causal Flow and the Function Machine

lain the > implications for robotics before everyone heads off to LA. I have drawn a > picture on the whiteboard in the office with a design which leverages this > idea in a physical topology suitable for human robot legs. > > - Curtis > > > > -- Ben Goertzel, P

Re: [opencog-dev] Re: Symmetric Causal Flow and the Function Machine

ware-only and both together at once. I'm going to dig > into Object Capabiliies. Any suggestion for people or places to start? > > On Mon, Jul 17, 2017 at 11:32 AM, Ben Goertzel <b...@goertzel.org> wrote: >> >> Hmmm... the context is quite different, but I am rem

Re: [opencog-dev] Android port (GUI and NDK engine build)

it this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/8f0e0a9d-3279-4e3d-a420-6104ec6fbac6%40googlegroups.com. > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http:/

Re: [opencog-dev] Re: Intu is opened sourced by IBM

nstraint_satisfaction_problem >> >> I randomly picked through the other directories, and ... was not >> impressed. My general impression is that its like something one might have >> seen in the 1980's-1990's, in the dark of AI winter. SGI had whizzier stuff >> back then

  1   2   3   4   >