Fractally-organized Connectionist Networks: Conjectures and Preliminary Results

TL;DR

This paper explores the idea that connectionist networks can be organized fractally to manage complexity effectively, potentially extending their application to complex domains like sociotechnical systems, with preliminary evidence from a telemonitoring software architecture.

Contribution

It introduces the concept of fractally organized connectionist networks as a means to encapsulate complexity and extend connectionism's applicability beyond simple networks.

Findings

Preliminary evidence from the design of a telemonitoring software architecture.

Fractal organization may enable connectionist networks to handle complex systems.

Supports the idea of relative simplicity over absolute simplicity in network design.

Abstract

A strict interpretation of connectionism mandates complex networks of simple components. The question here is, is this simplicity to be interpreted in absolute terms? I conjecture that absolute simplicity might not be an essential attribute of connectionism, and that it may be effectively exchanged with a requirement for relative simplicity, namely simplicity with respect to the current organizational level. In this paper I provide some elements to the analysis of the above question. In particular I conjecture that fractally organized connectionist networks may provide a convenient means to achive what Leibniz calls an "art of complication", namely an effective way to encapsulate complexity and practically extend the applicability of connectionism to domains such as sociotechnical system modeling and design. Preliminary evidence to my claim is brought by considering the design of the software architecture designed for the telemonitoring service of Flemish project "Little Sister".