Exceeding Computational Complexity Trial-and-Error Dynamic Action and Intelligence

TL;DR

This paper explores how intelligence science concepts can be applied to surpass traditional computational complexity limits, proposing a trial-and-error dynamic search framework exemplified by the Number Partition Problem.

Contribution

It introduces new concepts like unparticularized and particularized computing, and proposes a trial-and-error + dynamic search framework to address complex problems beyond standard computational bounds.

Findings

Framework demonstrates potential to exceed traditional computational limits.

Application to Number Partition Problem illustrates effectiveness.

New definitions clarify alternative computing paradigms.

Abstract

Computational complexity is a core theory of computer science, which dictates the degree of difficulty of computation. There are many problems with high complexity that we have to deal, which is especially true for AI. This raises a big question: Is there a better way to deal with these highly complex problems other than bounded by computational complexity? We believe that ideas and methods from intelligence science can be applied to these problems and help us to exceed computational complexity. In this paper, we try to clarify concepts, and we propose definitions such as unparticularized computing, particularized computing, computing agents, and dynamic search. We also propose and discuss a framework, i.e., trial-and-error + dynamic search. Number Partition Problem is a well-known NP-complete problem, and we use this problem as an example to illustrate the ideas discussed.