Re: [opencog-dev] Calling forward/backward chainer

There were some errors in the readme, now corrected. Nil On 04/02/2017 11:22 PM, Alex wrote: I am also trying to run this https://github.com/opencog/atomspace/tree/master/examples/rule-engine/chaining example and I enter SCM commands one by one and I am also stopped at lines DefineLink

Re: [opencog-dev] Calling forward/backward chainer

Hi, here are the steps to take in order to define rules and a rule base for the chainer: step 1. Define the rules eg. (define Rule_A (BindLink) ) Step 2. Create a DefineLink eg. (DefineLink (DefinedSchemaNode "Rule_A") Rule_A) Step 3. Define a rulebase eg. (define RuleBase_X

Re: [opencog-dev] Questions on a Knowledge Representation Standard for AGI - Help me not waste my time :-)

Hi Linas, Thanks for the response below and good counter examples. Agreed on your point regarding the modifiers and models. I've been trying to consider both natural language and basic scenes (eg. camera etc) this week, but even on the most trivial cases, I'm finding that I need many

Re: [opencog-dev] Calling forward/backward chainer

I am also trying to run this https://github.com/opencog/atomspace/tree/master/examples/rule-engine/chaining example and I enter SCM commands one by one and I am also stopped at lines DefineLink (define rule1-name (Node "rule1") *(DefineLink rule1-name rule1)* DefineLinke requires as the

Re: [opencog-dev] Should we encode the basic cognitive procedures (initial version at least) or they will spring out automatically?

Hi Alex, I'm hoping for a two-prong approach for some of the simpler stages of what you talk about: hand-coded rules, for now, to get some things going, and then also some automatically-learned ... uhh .. things. The hanson-robots chatbot consists of multiple parts, some of which are very

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

Hi Ben, On Sun, Apr 2, 2017 at 3:16 PM, Ben Goertzel wrote: > So e.g. if we find X+Y is roughly equal to Z in the domain > of semantic vectors, > But what Jesus is saying (and what we say in our paper, with all that fiddle-faddle about categories) is precisely that while

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

My quick, informal gut-feel sense of this is that the right answer is to replace "vector" part of word2vec by that *actual data structure* that *actually occurs in language". It's kind of hard to explain how to do this, but let me give it a whirl. Note how vectors are "symmetric", in the sense

Re: [opencog-dev] Questions on a Knowledge Representation Standard for AGI - Help me not waste my time :-)

Hi Adam, My personal instinct is that a human-curated KR system is kind-of pointless. Let me explain why. I've actually tired to create one several times now, and have been dis-satisfied with the results. The first time, I thought Icould do it with "semantic triples" -- subject-verb-object type

[opencog-dev] Re: Questions on a Knowledge Representation Standard for AGI - Help me not waste my time :-)

Same for me. I'm quite new to OWL2, but looking at some of the reasoning that's possible over well thought out ontologies generated by humans is what got me thinking. In terms of features, I'm building a laundry list of things that OWL2 doesn't support readily. Most of these so far have been

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

Yeah, good that you bring that up! Linas and I have read Coecke's papers on this stuff and discussed them a few times Indeed we are well positioned to explore these sorts of ideas computationally... I suppose the value of the morphism you cite in a practical context would be: If patterns

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

Dear Dr. Goertzel and contributors, You could also enrich the distributional ideas giving support to compositionality in other way. In your arxiv:1703.04368 you link a pregroup grammar parse tree of a sentence to a morphism in a symmetric monoidal category. In work from Coecke, Clark and

[opencog-dev] Re: [Problem] Compiling Opencog on Ubuntu 16.04 and Boost 1.58

Thanks Nil and linas, i disabled cpprest download and opencog is now built. I'm getting 86% on unit test, so i think it's working ^^ Thank you both Jérémy -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubscribe from this group and stop