Prior Draft AGI Ontology
From AGIRI.org
Glossary of terms
Perception -- Converting the (3+1)D sensory experience to a symbolic form (ie the internal knowledge representation). For example, a symbolic form may be "On(apple,table)" signifying the apple is on the table.
Symbol grounding -- may refer to several concepts; one of which is: "Sensory" symbol grounding -- Any means by which a symbolic representation becomes non-arbitrary because of its binding to sensory experience. For example the word "apple" can be an arbitrary signifier. The mapping of the word "apple" to a node that detects apples from the vision sensors enables the binding of the word to sensory experience.
Logic -- usually refers to FOL (first order predicate logic). FOL includes predicates, variables, functions, and the universal and existential quantifiers. For some knowledge representation purposes using a subset of FOL may be desirable. One subset is Horn logic.
Emergence --
Self-organization --
Working Memory -- A conduit for information exchange among modules. WM is passive in the sense that it does not modify its contents.
Planner module -- The module responsible for solving complex problems. It communicates with other modules by issuing commands to or requesting information from them. It has supreme executive power in the sense that its commands override other modules such as the inference engine.
Inference Engine -- Performs logical inference (including induction, abduction and deduction) from premises in Working Memory.
Pattern Recognizer -- aka Concept Recognizer -- Recognizes patterns in Working Memory. For example, if 2 eyes, 1 nose, 1 mouth on a head is presented as facts in WM, then the "face" pattern is recognized and the result is added to WM as a new fact.
Knowledge maintenance module -- Maintains the integrity of the knowledgebase, ie Semantic and Generic Memories. For example, deciding which one of several conflicting facts/rules should be retracted or modified.
Fact -- A logical statement, eg "Kicks(john,mary,t1)" meaning that John kicks Mary at time t1.
Rule -- A general logical statement, ie one with variables. For example "forall x: Man(x)->Mortal(x)" means that all men are mortal.
Inductive learning module -- Performs "data-mining" functions. Given some facts in WM, discover general rules that cover them. For example, from many instances of women having long hair generalize that women have long hair with probability p.
Natural Language Processor -- Performs the mapping of natural language to and from the internal knowledge representation. This mapping may also be defined by modifiable rules, thus allowing language learning.
Semantic memory -- Stores the meanings of concepts, ie, the definition of concepts / patterns. For example, the definition of "face" in terms of eyes, nose, mouth, and their relative positions, etc.
Episodic memory -- Events that happened in sensory experience, with a specific timestamp.
Generic memory -- Any knowledge that is not episodic, excluding semantic memory. For example, "entropy is the measure of disorder", or "Boltzmann commited suicide in 1906". (In cognitive psychology, this term includes semantic memory, we exclude it.)
Procedural memory -- In cognitive psychology, procedural memory is not accessible to conscious thinking, for example, how to walk or how to ride a bicycle. We use this term to mean a repository of knowledge for the Planner module. That means any knowledge gained by the Planner about how to solve problems.
Procedural learning -- Any form of learning occuring inside the Planner module. The Planner gains knowledge of how to solve complex problems and stores such knowledge in Procedural Memory.
