# Nonmodular architectures of cognitive systems based on active inference

## TL;DR

This paper critiques traditional modular, feedforward models of cognition and proposes a nonmodular, active inference-based architecture that is more robust to environmental uncertainties and external forces.

## Contribution

It introduces a novel nonmodular sensorimotor architecture based on active inference, challenging the separation principle in control theory and traditional cognitive models.

## Key findings

- The nonmodular architecture is robust to unknown external inputs.
- Linear models of the architecture are equivalent to integral control.
- The approach demonstrates limitations of separation-based models in dynamic environments.

## Abstract

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 the active inference framework. 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.