World model learning and inference
Open accessThe DOI matches its Crossref record; 85 of the 85 references it cites were found in a registry or an index.
Abstract
Understanding information processing in the brain-and creating general-purpose artificial intelligence-are long-standing aspirations of scientists and engineers worldwide. The distinctive features of human intelligence are high-level cognition and control in various interactions with the world including the self, which are not defined in advance and are vary over time. The challenge of building human-like intelligent machines, as well as progress in brain science and behavioural analyses, robotics, and their associated theoretical formalisations, speaks to the importance of the world-model learning and inference. In this article, after briefly surveying the history and challenges of internal model learning and probabilistic learning, we introduce the free energy principle, which provides a useful framework within which to consider neuronal computation and probabilistic world models. Next, we showcase examples of human behaviour and cognition explained under that principle. We then describe symbol emergence in the context of probabilistic modelling, as a topic at the frontiers of cognitive robotics. Lastly, we review recent progress in creating human-like intelligence by using novel probabilistic programming languages. The striking consensus that emerges from these studies is that probabilistic descriptions of learning and inference are powerful and effective ways to create human-like artificial intelligent machines and to understand intelligence in the context of how humans interact with their world.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
The free-energy principle: a unified brain theory?
Friston, K. (2010) · Nature Reviews Neuroscience · doi:10.1038/nrn2787 · Cited by 8,120 · cited 2×
“Neuroscience and computational studies have suggested that the free energy principle (Friston, 2010; Friston, Kilner, & Harrison, 2006) and predictive coding or processing (Clark, 2013b; Rao & Ballard, 1999) provide a unified account for cognitive development (Nagai, 2019).”
BackgroundSelf-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
Whatever next? Predictive brains, situated agents, and the future of cognitive science
Clark, A. (2013) · Behavioral and Brain Sciences · doi:10.1017/s0140525x12000477 · Cited by 5,924 · cited 2×
“Sometimes this is a more difficult problem that estimating the average or expectation of an unknown (Clark, 2013a; Hohwy, 2013).”
BackgroundRao, R. P. N., & Ballard, D. H. (1999) · Nature Neuroscience · doi:10.1038/4580 · Cited by 5,483 · cited 2×
“For example, with generative models of continuous states, we end up with predictive coding schemes (Rao & Ballard, 1999; Srini-vasan, Laughlin, & Dubs, 1982) that, in engineering, correspond to Bayesian filters, e.g., extended Kalman and particle filters (Lee & Mumford, 2003; Loeliger, 2002).”
BackgroundMethodThe faculty of language: what is it, who has it, and how did it evolve?
Hauser, M. D., Chomsky, N., & Fitch, W. T. (2002) · Science · doi:10.1126/science.298.5598.1569 · Cited by 5,189
Mindblindness: An Essay on Autism and Theory of Mind
(1995) · Choice Reviews Online · doi:10.5860/choice.33-2412 · Cited by 3,670
Mindblindness: An Essay on Autism and Theory of Mind
Baron-Cohen, S. (1995) · doi:10.7551/mitpress/4635.001.0001 · Cited by 3,428
Neurophysiological mechanisms underlying the understanding and imitation of action
Rizzolatti, G., Fogassi, L., & Gallese, V. (2001) · Nature Reviews Neuroscience · doi:10.1038/35090060 · Cited by 3,302
Cited by
Reconsidering autistic ‘camouflaging’ as transactional impression management
Ai, W., Cunningham, W. A., & Lai, M.-C. (2022) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2022.05.002 · Cited by 140
Emergent communication through Metropolis-Hastings naming game with deep generative models
Taniguchi, T., Yoshida, Y., Matsui, Y., Le Hoang, N., Taniguchi, A., & Hagiwara, Y. (2023) · Advanced Robotics · doi:10.1080/01691864.2023.2260856 · Cited by 33
“The world model -based approach to artificial intelligence also follows this view [42,43].”
BackgroundSelf-citationCollective predictive coding hypothesis: symbol emergence as decentralized Bayesian inference
Taniguchi, T. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1353870 · Cited by 28
“In contrast, world models are representation-learning models that include action outputs (Ha and Schmidhuber, 2018; Friston et al., 2021).”
BackgroundInfluentialSelf-citationFox, S., & Rey, V. F. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6030071 · Cited by 22
“Different interpretations of the same information can arise because different people have different internal models of self in the world, which, for brevity, can be referred to as world models [11].”
BackgroundDi Paolo, L. D., White, B., Guénin-Carlut, A., Constant, A., & Clark, A. (2024) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2023.0148 · Cited by 14
Metadata
- Authors
- Friston, K., Moran, R. J., Nagai, Y., Taniguchi, T., Gomi, H., & Tenenbaum, J.
- Venue
- Neural Networks
- Publisher
- Elsevier BV
- Published
- 2021-12
- Volume
- 144
- Pages
- 573-590
- ISSN
- 0893-6080 (ISSN-L)
- OpenAlex
- W3200610390
- Cited by
- 90
- References
- 85
- FWCI
- 6.59
- Type
- journal article
- Language
- en
- Open access
- hybrid
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: World model learning and inference. https://app.cochat.ai/papers/10.1016/j.neunet.2021.09.011
- The paper
- Friston, K., Moran, R. J., Nagai, Y., Taniguchi, T., Gomi, H., & Tenenbaum, J. (2021). World model learning and inference. Neural Networks. https://doi.org/10.1016/j.neunet.2021.09.011
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.