Representing Knowledge

[bperet]

I have recently done a lot of research on Knowledge systems, and how knowledge is represented. From this, I created a neural network program, that simulates the way concepts and associations are stored in the brain. Now I am faced with the challenge of how to actually populate such a system, because one of the things that becomes apparent is that there cannot be any "assumptions" made... everything has to be put in context.

The program creates "neurons", which have several attributes:

1) Context. Each neuron has a linkage to a context neuron, like a "parent concept". Spatial location is highly contextual. For example, your pillow is on the context of your bed, which is in the context of the bedroom, in the context of the home, in the context of the street in the context of the neighborhood,... etc, on and on, right up to the planet Earth, in the Sol solar system, and whatever galactic arrangments occur beyond that. It is how one would "zoom in" to the neuron, along a specific, and unique, path from the origin of all.

In the program, each neuron has only ONE context it can be in. A pillow cannot be on the bed and on the sofa at the same time.

I will admit that I still have some more conceptual work to do on the "temporal context" within the program design, because you CAN have the same pillow on the bed and on the sofa, at different TIMES. Right now, I am addressing Time thru "association", described later. But I feel there is a better way; just cannot see it yet.

"Context" is often referred to as "scope" in other knowledge systems.

2) A unique "base name" that allows us, as humans, to attach some sort of conceptual meaning to the neuron. Base names must be UNIQUE within their context. For example, "Mercury" has multiple contexts: a planet, an element, an automobile, etc. The base name of "Mercury" would work in all three examples, because they would be within the context of Astronomy, Physics and Vehicles, respectively.

3) Associative references. In order to address the non-local characteristics of connectivity, neurons can also associate other neurons in a "player--role" model. For example, in the context of "Human relationships", one has a "Family" assocation. Within that association, there are players and roles -- mother, father, son, daughter, etc. The "player" linkage of a neuron refers to what is being acted on, and the "role" links the action.

4) Facets of Information. Neurons can contain specific facets of knowledge. For example, a "Bruce's Birthday" neuron would have a facet of the date and time I was born. I have included facets for the concepts of text, numbers, date-times, URLs and comments. These facets are used for dynamic information, analogous to "short term memory" in the brain. Common usage of a facet on a computer system would be a username, password, email address, etc., which can be altered, without changing the base concepts.

I realize that this is a "short cut", and that all information can be represented via the original concept/association model. I did actually attempt such a program, but the overhead became phenomenonal, since even things like character sets had to be represented, and associations to form words in cryllic systems. This is here more for practicality, than conceptual design.

The neural network program I have created (and will have online shortly), simply creates and stores neurons. But it knows nothing to start... the next challenge is to take the concepts of the Reciprocal System, and give them context, association and facet. And believe me, it points out errors in logical deduction VERY quickly!

I will be following up with my ideas on how to create an RS knowledge structure, based on this model.

[bperet]

The first problem I ran into, when attempting to codify RS knowledge, was that the initial concept has no context. I had to adjust for this, to allow for context-free concepts within the system, otherwise the database would refuse to create anything--you had to have a neuron to create a neuron. Kind of a "catch-22" situation. So, I have a mechanism to create null-context neurons, which are basic concepts, or simply un-linked contexts that act as starting points of a tree of knowledge.

In the Reciprocal System, the very first "concept", to which there is no context, is that of Unity. This agrees with other metaphysical sources that state "all is ONE." This one is easy:

(null context) Basename: Unity

The next concept that occurs is:

Larson's RS: direction reversal

Law of One: free will (opposition to conformity to unity)

RS2: displacement

The idea is the same, in all three references... something happens, that causes a deviation from unit motion. But this also brings up another interesting problem--it would be nice to represent multiple perspectives of this information, that reference these base concepts. Like different views in a hologram. By looking at multiple perspectives, we might be able to find the precise, underlying concepts from which they are derived.

Before going any further, I decided to create another "context-free" concept, the concept of "Theory", which provides context for three other conceptual members, "RS", "RS2" and "Law of One". This also provides an open door for other systems of science and philosophy to link in.

(null context) Basename: Theory

(Theory) Reciprocal System (Dewey B. Larson's original work)

(Theory) Reciprocal System 2 (Peret/Nehru re-evaluation)

(Theory) Law of One (The Ra Material)

This idea of direction reversal, displacement, or free will have one, common attribute: they distort the concept of Unity in some way. So this information needs representation as neurons:

(Unity) Distortion

(RS) Direction Reversal

(RS2) Displacement

(Law of One) Free Will

We can then association these three paths to the distortion concept, based on theory:

(Direction Reversal) Role: Distortion, Player: Unity

(Displacement) Role: Distortion, Player: Unity

(Free Will) Role: Distortion, Player: Unity

This connects Unity to "distortion" (non-Unity), three ways. When retrieving information, one can provide the "Theory" in which to present information, and thus one can view the SAME structural and temporal relationships from the viewpoint of any theory defined. Should make for an interesting learning environment.

This is the basic idea of how a neural network functions. The challenge is how to define the "context-free" concepts, the contextual relationshpis and what the actual, underlying concepts are in all the viewpoints represented.

I could certainly use some help with this! Thanks.

[Guest]

Well, why not define the (null) context resources with the sub-concepts/contexts that use (null) as a reference?

There pretty much would be no clearly defined 'beginning' or 'end' in the system.

Maybe you could start it with (null) Unity. Then interjecting sub context and concepts would be the defining context for the (null) Unity object. In that sense too the structure can become recursive in a controlled way.

I suppose you could use a context linking name space or something, or XLinks to link to resources within the document itself.