Deep active inference
Open accessThe DOI matches its Crossref record; 73 of the 78 references it cites were found in a registry or an index.
Abstract
This work combines the free energy principle and the ensuing active inference dynamics with recent advances in variational inference in deep generative models, and evolution strategies to introduce the "deep active inference" agent. This agent minimises a variational free energy bound on the average surprise of its sensations, which is motivated by a homeostatic argument. It does so by optimising the parameters of a generative latent variable model of its sensory inputs, together with a variational density approximating the posterior distribution over the latent variables, given its observations, and by acting on its environment to actively sample input that is likely under this generative model. The internal dynamics of the agent are implemented using deep and recurrent neural networks, as used in machine learning, making the deep active inference agent a scalable and very flexible class of active inference agent. Using the mountain car problem, we show how goal-directed behaviour can be implemented by defining appropriate priors on the latent states in the agent's model. Furthermore, we show that the deep active inference agent can learn a generative model of the environment, which can be sampled from to understand the agent's beliefs about the environment and its interaction therewith.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“First, there is no expected free energy, instead the agent is trained to minimize the cumulated variational free energy over time.”
From Deconstructing Deep Active Inference: A Contrarian Information Gatherer (2024) · cites this paper as Ueltzhöffer (2018)
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Third, the DAI F A requires the modeller to encode the prior preferences within the distributions predicted by the encoder and transition network.This can limit the applicability of the approach.”
From Deconstructing Deep Active Inference: A Contrarian Information Gatherer (2024) · cites this paper as Ueltzhöffer (2018)
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Second, this approach unrolls the partially observable Markov decision process over time.In other words, the code builds a huge computational graph containing the encoder, decoder, transition and policy networks for each action-perception cycle.Therefore, the approach is computationally intensive and can become intractable for a large time horizon.”
From Deconstructing Deep Active Inference: A Contrarian Information Gatherer (2024) · cites this paper as Ueltzhöffer (2018)
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Although these packages are designed explicitly for reinforcement learning, which involves computing a reward metric at every state, they can also be used for Active Inference as they describe general control environments [24,17].”
From Reactive Environments for Active Inference Agents with RxEnvironments.jl (2025) · cites this paper as [24]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“This effectively propels the agent towards the target location.”
From Deconstructing Deep Active Inference: A Contrarian Information Gatherer (2024) · cites this paper as Ueltzhöffer (2018)
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 5×
“The chain rule gives: (2) Using these gradient estimates, we now optimise the expected free energy bound under the population density using ADAM as gradient based optimiser (Kingma and Ba, 2014).”
MethodInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · cited 1×
“2016) or style transfer or unsupervised image-to-image translation (Zhu et al. 2017; Liu et al. 2017).”
BackgroundMultilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · cited 14×
“…Agent do for t = 1 , ..., T do Sample an action ˆ a t from p θ ( a t | ˆ s t − 1 ) Propagate the environment using where only one sample per data point is enough, since the gradients depend on entire (mini-)batches of datapoints (Kingma and Welling, 2014; Rezende et al, 2014; Chung et al, 2015).”
BackgroundMethodInfluential(2016) · Cited by 11,679
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,081
The free-energy principle: a unified brain theory?
Friston, K. (2010) · Nature Reviews Neuroscience · doi:10.1038/nrn2787 · Cited by 8,120 · cited 2×
“…as well as anatomical and physiological features of the brain on one hand (Brown and Fris-ton, 2012; Friston, 2005; Friston et al, 2011; Friston and Kiebel, 2009; Schwartenbeck et al, 2015; Adams et al, 2013), and encompasses many formal theories about brain function on the other (Friston, 2010).”
BackgroundResultHumans integrate visual and haptic information in a statistically optimal fashion
Ernst, M. O., & Banks, M. S. (2002) · Nature · doi:10.1038/415429a · Cited by 4,844 · cited 2×
“explain hallmarks of Bayesian computations and probabilistic representations of sensory stimuli in the brain (Ernst and Banks, 2002; Alais and Burr, 2004; Knill and Pouget, 2004; Moreno-Bote et al, 2011; Berkes et al, 2011; Haefner et al, 2016).”
BackgroundMuJoCo: A physics engine for model-based control
Todorov, E., Erez, T., & Tassa, Y. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6386109 · Cited by 4,767 · cited 2×
“The Atari environments require an agent to learn to play Atari games from raw pixel or RAM input, while the 3D robotic environments use the MuJoCo physics engine (Todorov et al, 2012), to accurately simulate 3D robotic control problems.”
MethodInfluentialA theory of cortical responses.
Friston, K. (2005) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2005.1622 · Cited by 4,578 · cited 1×
“…for many aspects of action and perception as well as anatomical and physiological features of the brain on one hand (Brown and Fris-ton, 2012; Friston, 2005; Friston et al, 2011; Friston and Kiebel, 2009; Schwartenbeck et al, 2015; Adams et al, 2013), and encompasses many formal theories…”
BackgroundNeural Information Processing Systems
(2018) · The Deep Learning Revolution · doi:10.7551/mitpress/11474.003.0014 · Cited by 3,730
Why Does Unsupervised Pre-training Help Deep Learning?
Erhan, D., Bengio, Y., Courville, A. C., Manzagol, P.-A., Vincent, P., & Bengio, S. (2010) · Journal of Machine Learning Research · Cited by 2,631
The Bayesian brain: The role of uncertainty in neural coding and computation
Knill, D. C., & Pouget, A. (2004) · Trends in Neurosciences · doi:10.1016/j.tins.2004.10.007 · Cited by 2,588
Stochastic Backpropagation and Approximate Inference in Deep Generative Models
Rezende, D. J., Mohamed, S., & Wierstra, D. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1401.4082 · Cited by 2,405
Generative Adversarial Networks
(2022) · The Science of Deep Learning · doi:10.1017/9781108891530.013 · Cited by 2,402
The Ventriloquist Effect Results from Near-Optimal Bimodal Integration
Alais, D., & Burr, D. (2004) · Current Biology · doi:10.1016/j.cub.2004.01.029 · Cited by 1,936 · cited 1×
“This might explain hallmarks of Bayesian computations and probabilistic representations of sensory stimuli in the brain (Ernst and Banks, 2002; Alais and Burr, 2004; Knill and Pouget, 2004; Moreno-Bote et al, 2011; Berkes et al, 2011; Haefner et al, 2016).”
BackgroundCuriosity-Driven Exploration by Self-Supervised Prediction
Pathak, D., Agrawal, P., Efros, A. A., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.70 · Cited by 1,815 · cited 1×
“This is similar to recent work on artificial curiosity (Pathak et al, 2017).”
ResultStatic Analysis of Shape in TensorFlow Programs
The Theano Development Team, Al‐Rfou, R., Alain, G., Almahairi, A., Angermueller, C., Bahdanau, D., Ballas, N., Bastien, F., Bayer, J., Belikov, A., et al. (2016) · arXiv (Cornell University) · doi:10.4230/lipics.ecoop.2020.15 · Cited by 1,589 · cited 1×
“The code is written in Python 2.7, using Theano (Theano Development Team, 2016) for GPU optimised Tensor-Operations.”
MethodInfluentialPredictive coding under the free-energy principle
Friston, K., & Kiebel, S. (2009) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2008.0300 · Cited by 1,579
Hybrid computing using a neural network with dynamic external memory
Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwińska, A., Colmenarejo, S. G., Grefenstette, E., Ramalho, T., Agapiou, J., et al. (2016) · Nature · doi:10.1038/nature20101 · Cited by 1,412
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
Variational Inference with Normalizing Flows
Rezende, D. J., & Mohamed, S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.05770 · Cited by 1,253 · cited 1×
“…posterior is required, normalising flows allow a series of nonlinear transformations of the diagonal Gaussian used for the variational density, by which it can approximate very complex and multimodal posterior distributions (Rezende and Mohamed, 2015; Kingma et al, 2016; Tomczak and Welling, 2016).”
MethodActive 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
Every good regulator of a system must be a model of that system †
CONANT, R. C., & ROSS ASHBY, W. (1970) · International Journal of Systems Science · doi:10.1080/00207727008920220 · Cited by 1,063
A Recurrent Network Mechanism of Time Integration in Perceptual Decisions
Wong, K.-F., & Wang, X.-J. (2006) · The Journal of Neuroscience · doi:10.1523/jneurosci.3733-05.2006 · Cited by 1,029
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Salimans, T., Ho, J., Chen, X., Sidor, S., & Sutskever, I. (2017) · arXiv · doi:10.48550/arxiv.1703.03864 · Cited by 1,027 · cited 13×
“Here, no such artificially forced exploration is required, as the evolution strategies algorithm explores new solutions on the parameter space (Salimans et al, 2017).”
BackgroundMethodInfluentialPhoto-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A. P., Tejani, A., Totz, J., Wang, Z., et al. (2016) · arXiv (Cornell University) · doi:10.17863/cam.51996 · Cited by 987
Hierarchical Models in the Brain
Friston, K. (2008) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000211 · Cited by 952 · cited 3×
“Although this structure is on the first glance different from the hierarchical dynamical models developed by Friston (2008), the deep and nonlinear structure of the feedforward network also allows for structured noise to enter at different levels of this hierarchy.”
BackgroundMethodInfluentialAction and behavior: a free-energy formulation
Friston, K. J., Daunizeau, J., Kilner, J., & Kiebel, S. J. (2010) · Biological Cybernetics · doi:10.1007/s00422-010-0364-z · Cited by 866 · cited 18×
“Active Inference (Friston et al, 2006, 2010; Friston, 2012) is a normative theory of brain function derived from the properties required by active agents to survive in dynamic, changing environments.”
BackgroundMethodInfluentialThe Computational Anatomy of Psychosis
Adams, R. A., Stephan, K. E., Brown, H. R., Frith, C. D., & Friston, K. J. (2013) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2013.00047 · Cited by 850
Visualizing and Understanding Recurrent Networks
Karpathy, A., Johnson, J., & Fei-Fei, L. (2015) · arXiv · doi:10.48550/arxiv.1506.02078 · Cited by 845 · cited 7×
“By implementing the internal dynamics of our agent using deep neural networks (LeCun et al, 2015; Goodfellow et al, 2016) and recurrent dynamics (Karpathy et al, 2015), it is able to approximate the true generative process of its environment by its own generative model.”
BackgroundMethodInfluentialCorollary discharge across the animal kingdom
Crapse, T. B., & Sommer, M. A. (2008) · Nature Reviews Neuroscience · doi:10.1038/nrn2457 · Cited by 789
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
Friston, K. (2013) · Journal of The Royal Society Interface · doi:10.1098/rsif.2013.0475 · Cited by 754 · cited 1×
“This principle, in turn, is derived from necessary properties of dynamic systems in exchange with changing environments, which allow them to sustain their identity by keeping their inner parameters within viable bounds (Friston, 2012, 2013).”
BackgroundActive inference and epistemic value
Friston, K., Rigoli, F., Ognibene, D., Mathys, C., Fitzgerald, T., & Pezzulo, G. (2015) · Cognitive Neuroscience · doi:10.1080/17588928.2015.1020053 · Cited by 731
Every Good Regulator of a System Must Be a Model of That System
Conant, R. C., & Ashby, W. R. (1991) · Facets of Systems Science · doi:10.1007/978-1-4899-0718-9_37 · Cited by 712 · cited 1×
“Since the world in which we live is hierarchically organised, dynamic, and features a lot of complex noise, we assume that the agent’s model is a deep, recurrent, latent variable model (Conant and Ashby, 1970).”
BackgroundAction understanding and active inference
Friston, K., Mattout, J., & Kilner, J. (2011) · Biological Cybernetics · doi:10.1007/s00422-011-0424-z · Cited by 665
Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., & Zaremba, W. (2016) · arXiv · doi:10.48550/arxiv.1606.01540 · Cited by 582
The CMA Evolution Strategy: A TutorialPreprint
Hansen, N. (2005) · arXiv (Cornell University) · Cited by 580
ViZDoom: A Doom-based AI research platform for visual reinforcement learning
Kempka, M., Wydmuch, M., Runc, G., Toczek, J., & Jaskowski, W. (2016) · 2016 IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2016.7860433 · Cited by 541
A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
Le, Q. V., Jaitly, N., & Hinton, G. E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.00941 · Cited by 513 · cited 2×
“Note that each distribution is approximated by a single sample per time step per process. structures were shown to be able to efficiently learn and represent the underlying structure in complex time series data from real life applications (Karpathy et al, 2015; Le et al, 2015; Chung et al, 2015).”
BackgroundUnsupervised Image-to-Image Translation Networks
Liu, M.-Y., Breuel, T. M., & Kautz, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00848 · Cited by 477 · cited 1×
“2016) or style transfer or unsupervised image-to-image translation (Zhu et al. 2017; Liu et al. 2017).”
BackgroundA free energy principle for biological systems
Karl, F. (2012) · Entropy · doi:10.3390/e14112100 · Cited by 377 · cited 14×
“…of the free energy bound on the agent’s surprise, a subtle but important reinterpretation of the population density highlights the ubiquitous role of variational Bayes and the following minimisation of variational free energy (c.f. (Friston, 2012; Baez and Pollard, 2015; Harper, 2009)).”
InfluentialAnswering Schrödinger's question: A free-energy formulation
Ramstead, M. J. D., Badcock, P. B., & Friston, K. J. (2018) · Physics of Life Reviews · doi:10.1016/j.plrev.2017.09.001 · Cited by 354
Active Inference, Curiosity and Insight
Friston, K. J., Lin, M., Frith, C. D., Pezzulo, G., Hobson, J. A., & Ondobaka, S. (2017) · Neural Computation · doi:10.1162/neco_a_00999 · Cited by 351 · cited 3×
“…another, more natural way to include more complex prior expectations is to include one or more additional levels of latent variables and use simple priors on the more abstract levels to generate more complex, so called empirical priors on the lower levels (c.f. (Friston et al, 2017b) for a review).”
BackgroundWatson, R. A., & Szathmáry, E. (2016) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2015.11.009 · Cited by 324
Computation Beyond the Turing Limit
Siegelmann, H. T. (1995) · Science · doi:10.1126/science.268.5210.545 · Cited by 285 · cited 2×
“Similar to the approximation theorem for deep feedforward networks, it was shown that recurrent neural networks are able to learn arbitrary algorithms, as they are Turing complete (Siegelmann, 1995).”
BackgroundAuxiliary Deep Generative Models
Maaløe, L., Sønderby, C. K., Sønderby, S. K., & Winther, O. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.05473 · Cited by 241 · cited 1×
“2016; Tomczak and Welling 2016), auxiliary variables (Maaløe et al. 2016), or implicit representations (Mescheder et al.”
BackgroundDeep temporal models and active inference
Friston, K. J., Rosch, R., Parr, T., Price, C., & Bowman, H. (2017) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2017.04.009 · Cited by 237 · cited 3×
“By implementing the internal dynamics of our agent using deep neural networks (LeCun et al, 2015; Goodfellow et al, 2016) and recurrent dynamics (Karpathy et al, 2015), it is able to approximate the true generative process of its environment by its own generative model.”
BackgroundPerceptual Decision-Making as Probabilistic Inference by Neural Sampling
Haefner, R. M., Berkes, P., & Fiser, J. (2016) · Neuron · doi:10.1016/j.neuron.2016.03.020 · Cited by 207 · cited 1×
“This might explain hallmarks of Bayesian computations and probabilistic representations of sensory stimuli in the brain (Ernst and Banks, 2002; Alais and Burr, 2004; Knill and Pouget, 2004; Moreno-Bote et al, 2011; Berkes et al, 2011; Haefner et al, 2016).”
BackgroundHa, D., & Schmidhuber, J. (2018) · Zenodo · doi:10.5281/zenodo.1207631 · Cited by 187
Bayesian sampling in visual perception
Moreno-Bote, R., Knill, D. C., & Pouget, A. (2011) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1101430108 · Cited by 182
Improving Variational Inference with Inverse Autoregressive Flow
Kingma, D. P., Salimans, T., Józefowicz, R., Chen, X., Sutskever, I., & Welling, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04934 · Cited by 164
Moore, A. W. (1991) · Machine Learning Proceedings 1991 · doi:10.1016/b978-1-55860-200-7.50069-6 · Cited by 162 · cited 5×
“The agent will act in a discrete time version of the mountain car world (Moore 1991).”
BackgroundMethodInfluentialAdversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
Mescheder, L., Nowozin, S., & Geiger, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.04722 · Cited by 143 · cited 1×
“2016), or implicit representations (Mescheder et al. 2017; Huszár 2017).”
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 fact, evolution might be seen as a very similar learning process, only on different spatial and temporal scales (Watson and Szathmáry 2016; Baez and Pollard 2015; Harper 2009; Campbell 2016), where free energy is optimised on the level of species and ecosystems rather than individual agents (Friston 2012; Ramstead…”
BackgroundA Recurrent Latent Variable Model for Sequential Data
Chung, J., Kastner, K., Dinh, L., Goel, K., Courville, A. C., & Bengio, Y. (2026) · arXiv (Cornell University) · doi:10.5281/zenodo.19983308 · Cited by 119
Evidence for surprise minimization over value maximization in choice behavior
Schwartenbeck, P., FitzGerald, T. H. B., Mathys, C., Dolan, R., Kronbichler, M., & Friston, K. (2015) · Scientific Reports · doi:10.1038/srep16575 · Cited by 96 · cited 1×
“…as well as anatomical and physiological features of the brain on one hand (Brown and Friston, 2012; Friston, 2005; Friston et al, 2011; Friston and Kiebel, 2009; Schwartenbeck et al, 2015; Adams et al, 2013), and encompasses many formal theories about brain function on the other (Friston, 2010).”
BackgroundFree-Energy and Illusions: The Cornsweet Effect
Brown, H., & Friston, K. J. (2012) · Frontiers in Psychology · doi:10.3389/fpsyg.2012.00043 · Cited by 88 · cited 1×
“This theory is able to account formany aspects of action and perception as well as anatomical and physiological features of the brain, on the one hand (Brown and Friston 2012; Friston 2005; Friston et al. 2011; Friston and Kiebel 2009; Schwartenbeck et al. 2015; Adams et al. 2013), and encompasses many formal theories…”
Hierarchical Implicit Models and Likelihood-Free Variational Inference
Tran, D., Ranganath, R., & Blei, D. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.08896 · Cited by 86
Unsupervised Learning of 3D Structure from Images
Rezende, D. J., Eslami, S. M. A., Mohamed, S., Battaglia, P., Jaderberg, M., & Heess, N. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.00662 · Cited by 83 · cited 1×
“…of this agent uses methods that are applied to complex, large scale problems in machine learning and artificial intelligence (Chung et al, 2015; Rezende et al, 2016; Kingma et al, 2016), we hope that this class of agent can be of further use to demonstrate that active inference is able to…”
MethodRelative Entropy and Inductive Inference
Caticha, A. (2003) · CERN Document Server (European Organization for Nuclear Research) · Cited by 81
Improving Variational Auto-Encoders using Householder Flow
Tomczak, J. M., & Welling, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.09630 · Cited by 73 · cited 1×
“…posterior is required, normalising flows allow a series of nonlinear transformations of the diagonal Gaussian used for the variational density, by which it can approximate very complex and multimodal posterior distributions (Rezende and Mohamed, 2015; Kingma et al, 2016; Tomczak and Welling, 2016).”
MethodRelative Entropy in Biological Systems
Baez, J. C., & Pollard, B. (2016) · Entropy · doi:10.3390/e18020046 · Cited by 64 · cited 1×
“nger timescale over populations of agents by evolution. In fact, evolution might be seen as a very similar learning process, only on dierent spatial and temporal scales (Watson and Szathmary, 2016; Baez and Pollard, 2015; Harper, 2009). 3.3.6. The Free Energy Objective. Now we have everything that we need to put our o…”
BackgroundInfluentialVariational Inference using Implicit Distributions
Huszár, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.08235 · Cited by 57 · cited 1×
“2016), or implicit representations (Mescheder et al. 2017; Huszár 2017).”
BackgroundLearning to Act by Predicting the Future
Dosovitskiy, A., & Koltun, V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01779 · Cited by 56
An active inference implementation of phototaxis
Baltieri, M., & Buckley, C. L. (2017) · European Conference on Artificial Life · doi:10.7551/ecal_a_011 · Cited by 51
Relative Entropy and Inductive Inference
Caticha, A. (2004) · AIP conference proceedings · doi:10.1063/1.1751358 · Cited by 44
The Replicator Equation as an Inference Dynamic
Harper, M. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0911.1763 · Cited by 42 · cited 3×
“lations of agents by evolution. In fact, evolution might be seen as a very similar learning process, only on dierent spatial and temporal scales (Watson and Szathmary, 2016; Baez and Pollard, 2015; Harper, 2009). 3.3.6. The Free Energy Objective. Now we have everything that we need to put our objective function togeth…”
BackgroundInfluentialGuided Evolutionary Strategies: Escaping the curse of dimensionality in random search
Maheswaranathan, N., Metz, L., Tucker, G., Choi, D., & Sohl‐Dickstein, J. (2018) · Cited by 15
Research works printed but not linked: 2
- Karras T, Aila T, Laine S, Lehtinen J (2018) Progressive growing of gans for improved quality, stability, and variation. ICLR
- Theano Development Team (2016) Theano: a Python framework for fast computation of mathematical expressions. arXiv:1605.02688 · arXiv
Cited by
The free energy principle made simpler but not too simple
Friston, K., Da Costa, L., Sajid, N., Heins, C., Ueltzhöffer, K., Pavliotis, G. A., & Parr, T. (2023) · Physics Reports · doi:10.1016/j.physrep.2023.07.001 · Cited by 163
“Recently, there has been an increasing focus on active inference in the setting of machine learning and artificial intelligence [61,147,150,182–185].”
Self-citationActive Inference: Demystified and Compared
Sajid, N., Ball, P. J., Parr, T., & Friston, K. J. (2021) · Neural Computation · doi:10.1162/neco_a_01357 · Cited by 145
“…2017; Friston, Parr, et al., 2017; Parr & Friston, 2017), continuous state-space models (Buckley, Kim, McGregor, & Seth, 2017; Parr & Friston, 2019a; Ueltzhöffer, 2018) or mixed models with both discrete and continuous states as described in Friston, Parr, et al. (2017) and Parr and Friston (2018).”
Background(2021) · UCL Discovery (University College London) · Cited by 141
Friston, K., Da Costa, L., Hafner, D., Hesp, C., & Parr, T. (2021) · Neural Computation · doi:10.1162/neco_a_01351 · Cited by 117
“For example, Ueltzhöffer (2018) parameterized both the generative model and approximate posterior with function approximators, using evolutionary schemes to minimize variational free energy when gradients were not available.”
MethodInfluentialDeep active inference as variational policy gradients
Millidge, B. (2020) · Journal of Mathematical Psychology · doi:10.1016/j.jmp.2020.102348 · Cited by 115
Metadata
- Authors
- Ueltzhöffer, K.
- Corresponding author
- Ueltzhöffer, Kai
- ORCID
- Ueltzhöffer, Kai
- Venue
- Biological Cybernetics
- Published
- 2018-10-22
- Volume
- 112
- Issue
- 6
- Pages
- 547-573
- ISSN
- 0340-1200 (ISSN-L)
- 1432-0770
- OpenAlex
- W2753555157
- Cited by
- 98
- References
- 78
- Citations by year
- 2026: 5 · 2025: 9 · 2024: 9 · 2023: 14 · 2022: 7 · 2021: 31 · 2020: 18 · 2019: 4 · 2018: 1
- FWCI
- 7.97
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Biological Cybernetics (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Embodied and Extended Cognition
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference
- Keywords
- free energy principle, variational inference, deep generative models, latent variable models, evolution strategies, homeostasis, goal-directed behavior, recurrent neural networks, mountain car problem, active sampling
- MeSH terms
- Algorithms, Cognition, Environment, Goals, Humans, Models, Theoretical, Perception, Neural Networks, Computer, Nonlinear Dynamics
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
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.