140 likes | 148 Views
Title B ackground Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions. If intelligence is the ability to solve unanticipated problems, then artificial intelligence needs universal representations.
E N D
Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions If intelligence is the ability to solve unanticipated problems, then artificial intelligence needs universal representations Sergio Pissanetzky Sergio@SciControls.com
The Matrix Model of Computation (MMC) Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions Matrix of Services C Matrix of Sequences Q
Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions Properties of the MMC Any finitely realizable physical system can be perfectly represented by an MMC operating by finite means Mathematical Model for a formal Theory of Cognition 4 publications
Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions The Problem There is no AI in the MMC The Diagnostic You can not build artificial intelligence by taking away a system’s initiative and independence
The Solution Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions You take away a system’s initiative and independence when: ● You issue guarantees to services and imperatively control the behavior. ● You make it dependent on man-made structures. ● You reuse code or variables. ● You install multifunction services. ● Your issue incomplete specifications. C = Q =
The Result. The canonical form M = (C) Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions PROGRAM DATA
Profile Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions
Data channel Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions “Turbulent” flow
Service Commutation Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions
PROGRAM DATA G “Laminar” flow H G H G H
Canonical example and the act of learning 1 + 2 = 3 and 3 – 2 = 1
Equivalent circuit H H 1 + 2 = 3 and 3 – 2 = 1
Abstract machine H H 1 + 2 = 3 and 3 – 2 = 1
Title Background Properties Problem Solution Result Profile Data Channel Commutation Ontology Learning Circuit Abstr. mach. Conclusions Conclusions I have argued that: ● human intelligence obstructs AI ● AI structures must be universal, not ad-hoc I have proposed: ● transformations to remove man-made structures ● a new canonical form of the MMC ● an algorithm that can infer the ontology ● an algorithm for unlimited learning ● a universal abstract machine