Epstein Secrets

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

PLN Rules as GroundedSchemallodes PLN inference rules may be represented as GroundedSchemallodes. So for instance the PLN Deduction Rule, becomes a GroundedSchemallode with the properties: • Input: a pair of links (LI, L2), where LI and L2 are the same type, and must be one of InheritanceLink, ImplicationLink, Sub

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

asic backward step to carry out variable fulfillment queries as well as truth value queries. We may encapsulate these processes in the Atomspace as GroundedSchemallode: BasicForwardlnferenceStep GroundedSchemallode: BasicBackwardInferenceStep which take as input some Atom Al. and also as GroundedSchemallode: Att

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

get processor time, at which point in time. • Schema: A "script" describing a process to be carried out. This may be explicit, as in the case of a GroundedSchemallode, or implicit, as the case in Schema maps or ungrounded Schemallodes. • Schema Encapsulation: The process of automatically recognizing a Schema Map

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

get processor time, at which point in time. • Schema: A "script" describing a process to be carried out. This may be explicit, as in the case of a GroundedSchemallode, or implicit, as the case in Schema maps or ungrounded Schemallodes. • Schema Encapsulation: The process of automatically recognizing a Schema Map