Computing Networks: A General Framework to Contrast Neural and Swarm Cognitions

TL;DR

This paper introduces the Computing Networks framework to unify and compare neural and swarm architectures, revealing shared properties and differences that underpin complex cognition and computation across biological and artificial systems.

Contribution

It proposes a general framework (CNs) that models neural and swarm architectures, enabling their systematic comparison and analysis of properties related to cognition and computation.

Findings

CNs unify neural and swarm architectures

Shared properties enable complex cognition and computation

Multiple dynamical and functional scales are key to adaptation

Abstract

This paper presents the Computing Networks (CNs) framework. CNs are used to generalize neural and swarm architectures. Artificial neural networks, ant colony optimization, particle swarm optimization, and realistic biological models are used as examples of instantiations of CNs. The description of these architectures as CNs allows their comparison. Their differences and similarities allow the identification of properties that enable neural and swarm architectures to perform complex computations and exhibit complex cognitive abilities. In this context, the most relevant characteristics of CNs are the existence multiple dynamical and functional scales. The relationship between multiple dynamical and functional scales with adaptation, cognition (of brains and swarms) and computation is discussed.