• Home
  • Search
  • Deep Active Inference and Scene Construction.
  • Cite Icon28
  • https://doi.org/10.3389/frai.2020.509354Copy DOI Icon

Deep Active Inference and Scene Construction.

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Adaptive agents must act in intrinsically uncertain environments with complex latent structure. Here, we elaborate a model of visual foraging—in a hierarchical context—wherein agents infer a higher-order visual pattern (a “scene”) by sequentially sampling ambiguous cues. Inspired by previous models of scene construction—that cast perception and action as consequences of approximate Bayesian inference—we use active inference to simulate decisions of agents categorizing a scene in a hierarchically-structured setting. Under active inference, agents develop probabilistic beliefs about their environment, while actively sampling it to maximize the evidence for their internal generative model. This approximate evidence maximization (i.e., self-evidencing) comprises drives to both maximize rewards and resolve uncertainty about hidden states. This is realized via minimization of a free energy functional of posterior beliefs about both the world as well as the actions used to sample or perturb it, corresponding to perception and action, respectively. We show that active inference, in the context of hierarchical scene construction, gives rise to many empirical evidence accumulation phenomena, such as noise-sensitive reaction times and epistemic saccades. We explain these behaviors in terms of the principled drives that constitute the expected free energy, the key quantity for evaluating policies under active inference. In addition, we report novel behaviors exhibited by these active inference agents that furnish new predictions for research on evidence accumulation and perceptual decision-making. We discuss the implications of this hierarchical active inference scheme for tasks that require planned sequences of information-gathering actions to infer compositional latent structure (such as visual scene construction and sentence comprehension). This work sets the stage for future experiments to investigate active inference in relation to other formulations of evidence accumulation (e.g., drift-diffusion models) in tasks that require planning in uncertain environments with higher-order structure.

Loading PDF

Similar Papers
  • Research Article
  • Citations89

Neurocomputational mechanisms underlying emotional awareness: Insights afforded by deep active inference and their potential clinical relevance

  • Sep 10, 2019
  • Neuroscience & Biobehavioral Reviews
  • Ryan Smith +3
  • Research Article
  • Citations188

Active Inference: Demystified and Compared.

  • Jan 05, 2021
  • Neural Computation
  • Noor Sajid +3
  • Preprint Article

Behavioral and cognitive neuroscience findings regarding assumptions of the evidence accumulation model

  • Oct 24, 2023
  • Yikang Liu +1
  • Book Chapter
  • Citations3

Learning Generative Models for Active Inference Using Tensor Networks

  • Jan 01, 2023
  • Samuel T Wauthier +3
  • PDF
  • Conference Article
  • Citations32

Learning Perception and Planning With Deep Active Inference

  • May 01, 2020
  • Ozan Catal +4
  • PDF
  • Addendum
  • Citations124

Deep temporal models and active inference

  • May 08, 2018
  • Neuroscience & Biobehavioral Reviews
  • Karl J Friston +4
  • Research Article
  • Citations4

Auditory cortex neurons that encode negative prediction errors respond to omissions of sounds in a predictable sequence.

  • Jun 18, 2025
  • PLoS biology
  • Amit Yaron +5
  • PDF
  • Research Article
  • Citations16

Inter-trial effects in visual pop-out search: Factorial comparison of Bayesian updating models.

  • Jul 30, 2018
  • PLoS computational biology
  • Fredrik Allenmark +2
  • PDF
  • Research Article
  • Citations12

Small steps for mankind: Modeling the emergence of cumulative culture from joint active inference communication

  • Jan 09, 2023
  • Frontiers in Neurorobotics
  • Natalie Kastel +3
  • PDF
  • Research Article
  • Citations69

The impact of learning on perceptual decisions and its implication for speed-accuracy tradeoffs

  • Jun 02, 2020
  • Nature Communications
  • André G Mendonça +5
  • Research Article
  • Citations54

Evidence accumulation during perceptual decisions in humans varies as a function of dorsal frontoparietal organization.

  • Apr 20, 2020
  • Nature Human Behaviour
  • Méadhbh B Brosnan +8
  • Research Article
  • Citations746

Decision Making in Recurrent Neuronal Circuits

  • Oct 01, 2008
  • Neuron
  • Xiao-Jing Wang
  • Research Article
  • Citations3

The role of human intraparietal sulcus in evidence accumulation revealed by EEG and model-informed fMRI

  • Feb 14, 2025
  • bioRxiv
  • Jaeger Wongtrakun +5
  • Research Article
  • Citations47

Multi-Channel Decomposition in Tandem With Free-Energy Principle for Reduced-Reference Image Quality Assessment

  • Sep 01, 2019
  • IEEE Transactions on Multimedia
  • Wenhan Zhu +6
  • Book Chapter

Free-Energy Principle and Predictive Coding: A Computational Theory Explaining Various Brain Functions

  • Jan 01, 2026
  • Shingo Murata
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.