Ai Dreams Forum
Member's Experiments & Projects => General Project Discussion => Topic started by: frankinstien on November 23, 2021, 08:50:03 pm
-
I'm working with concepts as data expressed as a structure with properties and/or methods. I came up with some basic math shown below:
(https://i.imgur.com/M0iVEka.png)
Where concepts are the elements A,B,C,F,G,Q,Z, and T.
As shown in the diagram there are five basic operations along with the use of some set functions of union and intersection.
- Relatable to: can be expressed as grades or relevance.
- Indirectly relatable: indicates processing to relate to an element, which can also be viewed as a goal.
- Apply: is a process of utilizing verbs, adjectives, and adverbs that have expressions of properties and methods as well.
- Processes into: is a literal function that can produce a concept, e.g. computing the area of a table.
- not: is the anthesis of features or method outputs
Any concept can also be a set of concepts as hinted at by expressions 6 to 11. Also 4 hints at the ability to chain concepts to reach indirectly related concepts.
Pondering if this is complete enough, any thoughts?
-
Nice, but pretty abstract. Do you have any use examples?
-
All I can say is PROLOG probably is complete, not that I'm saying you might not be able to do better than it, or more concise or something, but I didn't learn much of it. With ordinary programming you are complete just with INVERT and a method of communing the variables, and thats it.
-
All I can say is PROLOG probably is complete, not that I'm saying you might not be able to do better than it, or more concise or something, but I didn't learn much of it. With ordinary programming you are complete just with INVERT and a method of communing the variables, and thats it.
I need the process to work in real-time without any need to compile code, yet need performance which is why I need a JIT (JIT has a 1% to 2% cost), which is why I didn't go with Prolog (https://en.wikipedia.org/wiki/Comparison_of_Prolog_implementations). There was some work done to build a ProLog JIT, but I don't know what happened to that endeavor. After looking at Rational consequence relation (https://en.wikipedia.org/wiki/Rational_consequence_relation) I can see that the approach I took needs a bit more refinement since it is too monotonic.
-
After looking at Rational consequence relation I can see that the approach I took needs a bit more refinement since it is too monotonic.
Actually, the monotonic issue isn't really an issue since it can be coped with using validation and in fact, this approach has the ability to note similarity, since it can grade its relatability.
-
Working with the parent-child relationship with the NLP parser made it hard to figure out what states and relationships exist amongst the different segments of a sentence, also figuring out the sequence of the phrases wasn't available either, however, it does have a child index method, but I need a bigger picture concept to work relationships based on parts of speech and word descriptions or definitions. So the vertical structure is a self-similar object that has a descriptor base abstraction class. This allows for a sentence to be relatable to individual words, phrases, and other sentences. So, with this kind of structure iterating through it is easy enough, it can also allow itself to be analyzed in parallel, so all phrases can get processed simultaneously and the big helper is that one can jump around the sentence for a look ahead process that helps prep analysis.
Click on the image to get a bigger pic.
(https://i.imgur.com/aU7JZdS.png) (https://i.imgur.com/aU7JZdS.png)
-
Have you explored semantic parsing techniques such as Combinatory Categorial Grammar?
https://groups.inf.ed.ac.uk/ccg/software.html (https://groups.inf.ed.ac.uk/ccg/software.html)