A Factor Graph Description of Deep Temporal Active Inference
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Active inference is a corollary of the Free Energy Principle that prescribes how self-organizing biological agents interact with their environment. The study of active inference processes relies on the definition of a generative probabilistic model and a description of how a free energy functional is minimized by neuronal message passing under that model. This paper presents a tutorial introduction to specifying active inference processes by Forney-style factor graphs (FFG). The FFG framework provides both an insightful representation of the probabilistic model and a biologically plausible inference scheme that, in principle, can be automatically executed in a computer simulation. As an illustrative example, we present an FFG for a deep temporal active inference process. The graph clearly shows how policy selection by expected free energy minimization results from free energy minimization per se, in an appropriate generative policy model.
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
Canonical Microcircuits for Predictive Coding
Bastos, A. M., Usrey, W. M., Adams, R. A., Mangun, G. R., Fries, P., & Friston, K. J. (2012) · Neuron · doi:10.1016/j.neuron.2012.10.038 · Cited by 2,421 · cited 1×
“Rather than relying on automated-inference toolboxes, there have been attempts to develop a biologically viable process theory for active inference processes (Bastos et al., 2012; Friston et al., 2017a).”
MethodSelf-citationA 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 · cited 1×
“, stay alive) through the single mechanism of minimizing the variational free energy under a model of their environment (which is equivalent to maximizing the Bayesian evidence for that model) (Friston et al., 2006; Friston, 2012).”
BackgroundSelf-citationCerebral hierarchies: predictive processing, precision and the pulvinar
Kanai, R., Komura, Y., Shipp, S., & Friston, K. (2015) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2014.0169 · Cited by 432 · cited 1×
“In real neural circuits, multiple parallel operating active inference columns may directly affect the dynamic beliefs over precisions in other columns through message passing over lateral connections (Kanai et al., 2015).”
BackgroundSelf-citationThe graphical brain: Belief propagation and active inference
Friston, K. J., Parr, T., & de Vries, B. (2017) · Network Neuroscience · doi:10.1162/netn_a_00018 · Cited by 415
Self-citationA free energy principle for biological systems
Karl, F. (2012) · Entropy · doi:10.3390/e14112100 · Cited by 377 · cited 1×
“, stay alive) through the single mechanism of minimizing the variational free energy under a model of their environment (which is equivalent to maximizing the Bayesian evidence for that model) (Friston et al., 2006; Friston, 2012).”
BackgroundUniversal darwinism as a process of bayesian inference
Campbell, J. O. (2016) · Frontiers in Systems Neuroscience · doi:10.3389/fnsys.2016.00049 · Cited by 140 · cited 1×
“In biological systems, model specification (the first task) occurs through evolutionary refinement by natural selection, which is also a manifestation of free energy minimization at a large time scale (Harper, 2009; Campbell, 2016).”
Background
Cited by
A step-by-step tutorial on active inference and its application to empirical data
Smith, R., Friston, K. J., & Whyte, C. J. (2022) · Journal of Mathematical Psychology · doi:10.1016/j.jmp.2021.102632 · Cited by 246
Self-citationCorcoran, A. W., Pezzulo, G., & Hohwy, J. (2020) · Biology & Philosophy · doi:10.1007/s10539-020-09746-2 · Cited by 161
Generative models for active vision
Parr, T., Sajid, N., Da Costa, L., Mirza, M. B., & Friston, K. J. (2021) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2021.651432 · Cited by 46
Self-citationHierarchical Gaussian Filtering of Sufficient Statistic Time Series for Active Inference
Mathys, C., & Weber, L. (2020) · Communications in Computer and Information Science · doi:10.1007/978-3-030-64919-7_7 · Cited by 8
Metadata
- Authors
- de Vries, B., & Friston, K. J.
- Venue
- Frontiers in Computational Neuroscience
- Publisher
- Frontiers Media SA
- Published
- 2017-10-18
- Volume
- 11
- Pages
- 95-95
- ISSN
- 1662-5188 (ISSN-L)
- OpenAlex
- W2767022047
- Cited by
- 26
- References
- 6
- FWCI
- 1.43
- 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: A Factor Graph Description of Deep Temporal Active Inference. https://app.cochat.ai/papers/10.3389/fncom.2017.00095
- The paper
- de Vries, B., & Friston, K. J. (2017). A Factor Graph Description of Deep Temporal Active Inference. Frontiers in Computational Neuroscience. https://doi.org/10.3389/fncom.2017.00095
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.