Epstein Secrets

nference Control 277 36.1 Introduction 277 36.2 High-Level Control Mechanisms 277 36.2.1 The Need for Adaptive Inference Control 278 36.3 Inference Control in PLN 279 36.3.1 Representing PLN Rules as GroundedSchemallodes 279 36.3.2 Recording Executed PLN Inferences in the Atomspace 279 36.3.3 A

entioned: 1. Via preprocessing of perceptual inputs (e.g. the names of NumberNode, CharacterNodes) 2. Via hard-wiring of names for Schemallodes and PredicateNodes corresponding to built-in elementary schema (e.g. +, AND, Say) If an Atom A has a name n in the system, we may write A.name n On the other hand,

hosen an alternate strategy for PLN. We have one inference control scheme, which is quite simple, but which relies partially on EFTA00624425 36.3 Inference Control in PLN 279 structures coming from outside PLN proper. The requisite variety of inference control strategies is provided by variety in the non-PLN

specification PredicateNode as true as possible). In evolutionary computing lingo, the specification predicate is a fitness function. Searching for PredicateNodes that embody patterns in the AtomSpace as a whole is a spe- cial case of this kind of learning, where the specification PredicateNode embodies a notio

36.3 Inference Control in PLN 281 36.3.4 Basic Forward and Backward Inference Steps The choice of an inference step, at the microscopic level, may be done in a number of

subgraphs containing Atom-valued variables . Each such subgraph may be represented as a PredicateNode, and frequent subgraph mining will find such PredicateNodes that have surprisingly high truth values when evaluated across the Atomspace. But unlike MOSES when applied as described above, such an algorithm wi