Hybrid predictive coding: Inferring, fast and slow

Guardado en:
Detalles Bibliográficos
Publicado en:PLoS Computational Biology vol. 19, no. 8 (Aug 2023), p. e1011280
Autor principal: Tscshantz, Alexander
Otros Autores: Beren Millidge https://orcid.org/0000-0003-1872-5635, Seth, Anil K, Buckley, Christopher L
Publicado:
Public Library of Science
Materias:
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 2865519787
003 UK-CbPIL
022 |a 1553-734X 
022 |a 1553-7358 
024 7 |a 10.1371/journal.pcbi.1011280  |2 doi 
035 |a 2865519787 
045 2 |b d20230801  |b d20230831 
084 |a 174831  |2 nlm 
100 1 |a Tscshantz, Alexander 
245 1 |a Hybrid predictive coding: Inferring, fast and slow 
260 |b Public Library of Science  |c Aug 2023 
513 |a Journal Article 
520 3 |a 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. 
653 |a Machine learning 
653 |a Visual perception 
653 |a Phenomenology 
653 |a Bayesian analysis 
653 |a Visual observation 
653 |a Iterative methods 
653 |a Pattern recognition 
653 |a Neural networks 
653 |a Signal processing 
653 |a Objective function 
653 |a Optimization 
653 |a Visual aspects 
653 |a Perception 
653 |a Consciousness 
653 |a Object recognition 
653 |a Predictions 
653 |a Statistical inference 
653 |a Coding 
653 |a Environmental 
700 1 |a Beren Millidge https://orcid.org/0000-0003-1872-5635 
700 1 |a Seth, Anil K 
700 1 |a Buckley, Christopher L 
773 0 |t PLoS Computational Biology  |g vol. 19, no. 8 (Aug 2023), p. e1011280 
786 0 |d ProQuest  |t Health & Medical Collection 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/2865519787/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/2865519787/fulltext/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/2865519787/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch