EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid predictive coding: Inferring, fast and slow

Alexander Tscshantz, Beren Millidge iD, Anil K Seth, Christopher L Buckley

PLOS Computational Biology · 02.08.2023 · 19 (8) · e1011280

DOI: 10.1371/journal.pcbi.1011280 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 02.08.2023. Verfasst von Alexander Tscshantz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Sussex AI Group, Department of Informatics, University of Sussex, Brighton, United Kingdom. Hauptthemen laut MEDLINE: Learning, Visual Perception. Die Arbeit wurde bisher 52-mal zitiert (Crossref) und nennt 149 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Biotechnology and Biological Sciences Research Council, European Research Council, Canadian Institute for Advanced Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predictive coding is an influential model of cortical neural activity. It proposes that perceptual beliefs are furnished by sequentially minimising “prediction errors”—the differences between predicted and observed data. Implicit in this proposal is the idea that successful perception requires multiple cycles of neural activity. This is at odds with evidence that several aspects of visual perception—including complex forms of object recognition—arise from an initial “feedforward sweep” that occurs on fast timescales which preclude substantial recurrent activity. Here, we propose that the feedforward sweep can be understood as performing amortized inference (applying a learned function that maps directly from data to beliefs) and recurrent processing can be understood as performing iterative inference (sequentially updating neural activity in order to improve the accuracy of beliefs). We propose a hybrid predictive coding network that combines both iterative and amortized inference in a principled manner by describing both in terms of a dual optimization of a single objective function. We show that the resulting scheme can be implemented in a biologically plausible neural architecture that approximates Bayesian inference utilising local Hebbian update rules. We demonstrate that our hybrid predictive coding model combines the benefits of both amortized and iterative inference—obtaining rapid and computationally cheap perceptual inference for familiar data while maintaining the context-sensitivity, precision, and sample efficiency of iterative inference schemes. Moreover, we show how our model is inherently sensitive to its uncertainty and adaptively balances iterative and amortized inference to obtain accurate beliefs using minimum computational expense. Hybrid predictive coding offers a new perspective on the functional relevance of the feedforward and recurrent activity observed during visual perception and offers novel insights into distinct aspects of visual phenomenology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LearningVisual PerceptionBayes Theorem

Autor:innen und Institutionen

  • Sussex AI Group, Department of Informatics, University of Sussex, Brighton, United Kingdom.
  • VERSES Research Lab, Los Angeles, California, United States of America.
  • Sussex Centre for Consciousness Science, University of Sussex, Brighton, United Kingdom.
  • Brain Networks Dynamics Unit, University of Oxford, Oxford, United Kingdom.

ORCID-Profile: Beren Millidge

Förderung

  • Biotechnology and Biological Sciences Research Council
  • European Research Council
  • Canadian Institute for Advanced Research
  • Dr. Mortimer and Theresa Sackler Foundation
  • School of Engineering and Informatics at the University of Sussex

Zitieren

APA

Tscshantz, A., Millidge, B., Seth, A. K., & Buckley, C. L. (2023). Hybrid predictive coding: Inferring, fast and slow. PLOS Computational Biology, 19(8), e1011280. https://doi.org/10.1371/journal.pcbi.1011280

Vancouver

Tscshantz A, Millidge B, Seth AK, Buckley CL. Hybrid predictive coding: Inferring, fast and slow. PLOS Computational Biology. 2023;19(8):e1011280. doi:10.1371/journal.pcbi.1011280

BibTeX
@article{Tscshantz2023,
  author = {Tscshantz, Alexander and Millidge, Beren and Seth, Anil K and Buckley, Christopher L},
  title = {Hybrid predictive coding: Inferring, fast and slow},
  journal = {PLOS Computational Biology},
  year = {2023},
  volume = {19},
  number = {8},
  pages = {e1011280},
  doi = {10.1371/journal.pcbi.1011280}
}
Kostenlos starten →