Canonical neural networks perform active inference
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
This work considers a class of canonical neural networks comprising rate coding models, wherein neural activity and plasticity minimise a common cost function—and plasticity is modulated with a certain delay. We show that such neural networks implicitly perform active inference and learning to minimise the risk associated with future outcomes. Mathematical analyses demonstrate that this biological optimisation can be cast as maximisation of model evidence, or equivalently minimisation of variational free energy, under the well-known form of a partially observed Markov decision process model. This equivalence indicates that the delayed modulation of Hebbian plasticity—accompanied with adaptation of firing thresholds—is a sufficient neuronal substrate to attain Bayes optimal inference and control. We corroborated this proposition using numerical analyses of maze tasks. This theory offers a universal characterisation of canonical neural networks in terms of Bayesian belief updating and provides insight into the neuronal mechanisms underlying planning and adaptive behavioural control.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The free-energy principle: a unified brain theory?
Friston, K. (2010) · Nature Reviews Neuroscience · doi:10.1038/nrn2787 · Cited by 8,120 · cited 7×
“(6) (see Methods section ‘Neural networks’ and Supplementary Methods 4 for further details).”
BackgroundResultInfluentialSelf-citationStatistical Decision Theory and Bayesian Analysis
Berger, J. O. (1985) · Springer Series in Statistics · doi:10.1007/978-1-4757-4286-2 · Cited by 7,722
Bi, G.-Q., & Poo, M.-M. (1998) · The Journal of Neuroscience · doi:10.1523/jneurosci.18-24-10464.1998 · Cited by 4,744
Malenka, R. C., & Bear, M. F. (2004) · Neuron · doi:10.1016/j.neuron.2004.09.012 · Cited by 3,968
The distinct modes of vision offered by feedforward and recurrent processing
Lamme, V. A. F., & Roelfsema, P. R. (2000) · Trends in Neurosciences · doi:10.1016/s0166-2236(00)01657-x · Cited by 2,338
(2000) · doi:10.2460/ajvr.67.2.323 · Cited by 1,621
A free energy principle for the brain
Friston, K., Kilner, J., & Harrison, L. (2006) · Journal of Physiology-Paris · doi:10.1016/j.jphysparis.2006.10.001 · Cited by 1,369
Self-citationActive inference: a process theory
Friston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P., & Pezzulo, G. (2017) · Neural Computation · doi:10.1162/neco_a_00912 · Cited by 1,156
Self-citationA cellular mechanism of reward-related learning
Reynolds, J. N. J., Hyland, B. I., & Wickens, J. R. (2001) · Nature · doi:10.1038/35092560 · Cited by 879
Spontaneous Cortical Activity Reveals Hallmarks of an Optimal Internal Model of the Environment
Berkes, P., Orbán, G., Lengyel, M., & Fiser, J. (2011) · Science · doi:10.1126/science.1195870 · Cited by 782
Cited by
The empirical status of predictive coding and active inference
Hodson, R., Mehta, M., & Smith, R. (2024) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2023.105473 · Cited by 69
The memory systems of the human brain and generative artificial intelligence
Rolls, E. T. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e31965 · Cited by 23
Fetal brain activity and the free energy principle
Miyagi, Y., Hata, T., & Miyake, T. (2023) · Journal of Perinatal Medicine · doi:10.1515/jpm-2023-0092 · Cited by 6
Da Costa, L., Seth, A. K., Friston, K., Ramstead, M. J. D., & Sandved-Smith, L. (2026) · Neuroscience of Consciousness · doi:10.1093/nc/niag026 · Cited by 3
Self-citationActive Inference in Hebbian Learning Networks
Safa, A., Verbelen, T., Keuninckx, L., Ocket, I., Bourdoux, A., Catthoor, F., Gielen, G., & Cauwenberghs, G. (2023) · arXiv · doi:10.48550/arxiv.2306.05053 · Cited by 2
Metadata
- Authors
- Isomura, T., Shimazaki, H., & Friston, K. J.
- Venue
- Communications Biology
- Published
- 2022-01-14
- Volume
- 5
- Issue
- 1
- Pages
- 55-55
- ISSN
- 2399-3642 (ISSN-L)
- OpenAlex
- W4205386412
- Cited by
- 67
- References
- 26
- FWCI
- 6.35
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Canonical neural networks perform active inference. https://app.cochat.ai/papers/10.1038/s42003-021-02994-2
- The paper
- Isomura, T., Shimazaki, H., & Friston, K. J. (2022). Canonical neural networks perform active inference. Communications Biology. https://doi.org/10.1038/s42003-021-02994-2
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.