A Mathematical Framework for Superintelligent Machines
Daniel J. Buehrer

TL;DR
This paper introduces a mathematical framework using class calculus and algebraic structures to enable self-improving, self-debugging, and self-modeling intelligent systems capable of complex reasoning and learning.
Contribution
It develops a novel class calculus based on class algebra and fuzzy logic, allowing machines to describe, analyze, and enhance their own learning and reasoning processes.
Findings
Framework can model self-improvement in learning systems
Uses class algebra to distinguish formula relationships
Incorporates fuzzy logic for probabilistic reasoning
Abstract
We describe a class calculus that is expressive enough to describe and improve its own learning process. It can design and debug programs that satisfy given input/output constraints, based on its ontology of previously learned programs. It can improve its own model of the world by checking the actual results of the actions of its robotic activators. For instance, it could check the black box of a car crash to determine if it was probably caused by electric failure, a stuck electronic gate, dark ice, or some other condition that it must add to its ontology in order to meet its sub-goal of preventing such crashes in the future. Class algebra basically defines the eval/eval-1 Galois connection between the residuated Boolean algebras of 1. equivalence classes and super/sub classes of class algebra type expressions, and 2. a residual Boolean algebra of biclique relationships. It…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Algebra and Logic · Rough Sets and Fuzzy Logic · Logic, Reasoning, and Knowledge
