Epstein Secrets

ImplicationLink_HOJ Inh SX stupid <.9> Inh SX rich <.97 EFTA00624176 30 20 Knowledge Representat

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,

VDIFF. Step A calculates the amount by which the rich have been made poorer, and uses this to make the

exts may be used in schema execution, but they're used only indirectly, via being passed to TruthValueEvaluators used for evaluating truth values of PredicateNodes or Com- poundTermNodes that occur internally in schemata being executed. EFTA00624272 EFTA00624273 Section III Perception and Action EFTA00624

29.7 Conclusion 189 flexibly interacting with a rich stream of data from the everyday human world. Thi

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

value query with target Al a InheritanceLink Bob rich Suppose the deduction rule It is chosen. Then i

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

g up a block in the dark is a perfect example of rich coupling of perception and action networks. Feeli

. • Imitation Learning: Learning via copying what some other agent is observed to do. • Implication: Often refers to an ImplicationLink between two PredicateNodes, indicating an (extensional, intensional or mixed) logical implication. • Implicit Knowledge Representation: Representation of knowledge via having

twork, in which a hierarchy exists, along with a rich network of heterarchical links joining nodes in t

. • Imitation Learning: Learning via copying what some other agent is observed to do. • Implication: Often refers to an ImplicationLink between two PredicateNodes, indicating an (extensional, intensional or mixed) logical implication. • Implicit Knowledge Representation: Representation of knowledge via having

etwork, in which a hierarchy exists, along with a rich network of heterarchical links joining nodes in t

er atoms. Grounded- PredicateNodes and GroundedSchemaNodes connect to explicitly represented procedures (sometimes in the Combo language); ungrounded PredicateNodes and SchemaNodes are abstract and, like ConceptNodes, purely characterized by their relationships. Node Probability: Many PLN inference rules rely on