Arbitrary Multiscale Explainable Decision-Making for Symbiotic Autonomous Systems

Abstract

In the near future to solve complex, arbitrary multiscale system problems, we need a unified, integrated framework that can offer an effective and convenient, universal mathematical approach, by considering information not only on the statistical manifold of model states, but also on the combinatorial manifold of low-level discrete, directed energy generators and empirical measures of noise sources, related to experimental high-level overall perturbation. To overcome past modeling limitations in dynamic cooperative multi-agent system, we propose the modeling of agent as purposive subject modeled by the Elementary Pragmatic Model (EPM) approach. In this context, predicative competence and natural language processing can play a fundamental role for developing a new generation of user-friendly, more autonomous, but still colloquial systems to offer explainable decision-making processes. In order to achieve this goal, a deep layer of “machine thought” is vital for developing highly competitive, reliable and effective symbiotic autonomous systems. Based on it, a new approach to computational predicative competence will be presented.