University of Sussex
Browse
ModularCognitiveModels (1).pdf (1.8 MB)

Nonmodular architectures of cognitive systems based on active inference

Download (1.8 MB)
conference contribution
posted on 2023-06-09, 17:41 authored by Manuel Baltieri, Christopher BuckleyChristopher Buckley
In psychology and neuroscience it is common to describe cognitive systems as input/output devices where perceptual and motor functions are implemented in a purely feedforward, open-loop fashion. On this view, perception and action are often seen as encapsulated modules with limited interaction between them. While embodied and enactive approaches to cognitive science have challenged the idealisation of the brain as an input/output device, we argue that even the more recent attempts to model systems using closed-loop architectures still heavily rely on a strong separation between motor and perceptual functions. Previously, we have suggested that the mainstream notion of modularity strongly resonates with the separation principle of control theory. In this work we present a minimal model of a sensorimotor loop implementing an architecture based on the separation principle. We link this to popular formulations of perception and action in the cognitive sciences, and show its limitations when, for instance, external forces are not modelled by an agent. These forces can be seen as variables that an agent cannot directly control, i.e., a perturbation from the environment or an interference caused by other agents. As an alternative approach inspired by embodied cognitive science, we then propose a nonmodular architecture based on active inference. We demonstrate the robustness of this architecture to unknown external inputs and show that the mechanism with which this is achieved in linear models is equivalent to integral control.

Funding

Distributed neural processing of self-generated visual input in a vertebrate brain; G2144; BBSRC-BIOTECHNOLOGY & BIOLOGICAL SCIENCES RESEARCH COUNCIL; BB/P022197/1

History

Publication status

  • Published

File Version

  • Accepted version

Journal

2019 International Joint Conference on Neural Networks (IJCNN): 2019 Proceedings

ISSN

2161-4407

Publisher

Institute of Electrical and Electronics Engineers

Event name

2019 International Joint Conference on Neural Networks (IJCNN)

Event location

Budapest, Hungary

Event type

conference

Event date

14-19 July 2019

ISBN

978-1-7281-1985-4

Department affiliated with

  • Informatics Publications

Research groups affiliated with

  • Evolutionary and Adaptive Systems Research Group Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2019-04-30

First Open Access (FOA) Date

2019-05-23

First Compliant Deposit (FCD) Date

2019-04-30

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC