Special Issue "Emerging Methods in Active Inference"

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Entropy and Biology".

Deadline for manuscript submissions: 11 July 2022 | Viewed by 4739

Special Issue Editors

Dr. Thomas Parr
E-Mail Website1 Website2
Guest Editor
The Wellcome Centre for Human Neuroimaging, UCL Queen Square Institute of Neurology, London WC1N 3BG, UK
Interests: active inference; Bayesian mechanics; theoretical neurobiology; computational neurology
Dr. Manuel Baltieri
E-Mail Website1 Website2 Website3 Website4
Guest Editor
Laboratory for Neural Computation and Adaptation, RIKEN Centre for Brain Science, Wakoshi, Saitama, Japan
Interests: active inference; sensorimotor control; action–perception loop; control theory; filtering theory; dynamical systems; cognitive computational neuroscience; artificial life
Dr. Thijs van de Laar
E-Mail Website
Guest Editor
Department of Electrical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands
Interests: active inference; variational methods; message passing; probabilistic programming
Dr. Kai Ueltzhöffer
E-Mail Website
Guest Editor
1. The Wellcome Centre for Human Neuroimaging, UCL Queen Square Institute of Neurology, London WC1N 3BG, UK
2. Department of General Psychiatry, Centre of Psychosocial Medicine, Heidelberg University Hospital, Voßstraße 2, 69115 Heidelberg, Germany
Interests: computational biology; theoretical neurobiology; deep generative models; stochastic thermodynamics; approximate Bayesian inference
Dr. Daniela Cialfi
E-Mail Website
Guest Editor
Department of Philosophical, Pedagogical and Economic-Quantitative Sciences, Economic and Quantitative Methods Section, University of Studies Gabriele d’Annunzio Chieti-Pescara, 65127 Pescara, Italy
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Karl Friston
grade E-Mail Website
Guest Editor
Queen Square Institute of Neurology, University College London, London, UK
Interests: theoretical neurobiology; computational neuroscience; neuroimaging; schizophrenia

Special Issue Information

Dear Colleagues,

Active inference is a formal approach for characterizing behavior. Although originally developed in theoretical neurobiology, it has found a diverse range of applications—from morphogenesis to robotics. Over the last few years, this range of applications has been matched with novel implementations of active inference. These vary along several dimensions. They exist for discrete or continuous time, as well as for continuous or categorical variables. Some versions use factor-graph-based message passing and variational inference, employing mean field or Bethe approximations. Others use Monte Carlo sampling schemes. Some focus on the underlying physics and Fokker–Planck formalisms. Others exploit technologies developed in deep learning and machine learning—such as the variational autoencoder—to facilitate application to large scale problems. This Special Issue aims to showcase the emerging spectrum of methods for active inference, as well as the kinds of questions they are designed to address.

Dr. Thomas Parr
Dr. Manuel Baltieri
Dr. Thijs van de Laar
Dr. Kai Ueltzhöffer
Dr. Daniela Cialfi
Prof. Dr. Karl Friston
Guest Editors

Ms. Noor Sajid
Assistant Guest Editor
Affiliation: The Wellcome Centre for Human Neuroimaging, UCL Queen Square Institute of Neurology, London WC1N 3BG, UK
Website: https://ucbtns.github.io/
Interests: active (variational) inference; degeneracy; adaptation

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • active inference
  • Bayesian
  • variational
  • stochastic
  • behavior
  • neural

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

Article
Goal-Directed Planning and Goal Understanding by Extended Active Inference: Evaluation through Simulated and Physical Robot Experiments
Entropy 2022, 24(4), 469; https://doi.org/10.3390/e24040469 - 28 Mar 2022
Viewed by 402
Abstract
We show that goal-directed action planning and generation in a teleological framework can be formulated by extending the active inference framework. The proposed model, which is built on a variational recurrent neural network model, is characterized by three essential features. These are that [...] Read more.
We show that goal-directed action planning and generation in a teleological framework can be formulated by extending the active inference framework. The proposed model, which is built on a variational recurrent neural network model, is characterized by three essential features. These are that (1) goals can be specified for both static sensory states, e.g., for goal images to be reached and dynamic processes, e.g., for moving around an object, (2) the model cannot only generate goal-directed action plans, but can also understand goals through sensory observation, and (3) the model generates future action plans for given goals based on the best estimate of the current state, inferred from past sensory observations. The proposed model is evaluated by conducting experiments on a simulated mobile agent as well as on a real humanoid robot performing object manipulation. Full article
(This article belongs to the Special Issue Emerging Methods in Active Inference)
Show Figures

Figure 1

Article
On Epistemics in Expected Free Energy for Linear Gaussian State Space Models
Entropy 2021, 23(12), 1565; https://doi.org/10.3390/e23121565 - 24 Nov 2021
Cited by 1 | Viewed by 702
Abstract
Active Inference (AIF) is a framework that can be used both to describe information processing in naturally intelligent systems, such as the human brain, and to design synthetic intelligent systems (agents). In this paper we show that Expected Free Energy (EFE) minimisation, a [...] Read more.
Active Inference (AIF) is a framework that can be used both to describe information processing in naturally intelligent systems, such as the human brain, and to design synthetic intelligent systems (agents). In this paper we show that Expected Free Energy (EFE) minimisation, a core feature of the framework, does not lead to purposeful explorative behaviour in linear Gaussian dynamical systems. We provide a simple proof that, due to the specific construction used for the EFE, the terms responsible for the exploratory (epistemic) drive become constant in the case of linear Gaussian systems. This renders AIF equivalent to KL control. From a theoretical point of view this is an interesting result since it is generally assumed that EFE minimisation will always introduce an exploratory drive in AIF agents. While the full EFE objective does not lead to exploration in linear Gaussian dynamical systems, the principles of its construction can still be used to design objectives that include an epistemic drive. We provide an in-depth analysis of the mechanics behind the epistemic drive of AIF agents and show how to design objectives for linear Gaussian dynamical systems that do include an epistemic drive. Concretely, we show that focusing solely on epistemics and dispensing with goal-directed terms leads to a form of maximum entropy exploration that is heavily dependent on the type of control signals driving the system. Additive controls do not permit such exploration. From a practical point of view this is an important result since linear Gaussian dynamical systems with additive controls are an extensively used model class, encompassing for instance Linear Quadratic Gaussian controllers. On the other hand, linear Gaussian dynamical systems driven by multiplicative controls such as switching transition matrices do permit an exploratory drive. Full article
(This article belongs to the Special Issue Emerging Methods in Active Inference)
Show Figures

Figure 1

Communication
Accessing Active Inference Theory through Its Implicit and Deliberative Practice in Human Organizations
Entropy 2021, 23(11), 1521; https://doi.org/10.3390/e23111521 - 15 Nov 2021
Cited by 2 | Viewed by 571
Abstract
Active inference theory (AIT) is a corollary of the free-energy principle, which formalizes cognition of living system’s autopoietic organization. AIT comprises specialist terminology and mathematics used in theoretical neurobiology. Yet, active inference is common practice in human organizations, such as private companies, public [...] Read more.
Active inference theory (AIT) is a corollary of the free-energy principle, which formalizes cognition of living system’s autopoietic organization. AIT comprises specialist terminology and mathematics used in theoretical neurobiology. Yet, active inference is common practice in human organizations, such as private companies, public institutions, and not-for-profits. Active inference encompasses three interrelated types of actions, which are carried out to minimize uncertainty about how organizations will survive. The three types of action are updating work beliefs, shifting work attention, and/or changing how work is performed. Accordingly, an alternative starting point for grasping active inference, rather than trying to understand AIT specialist terminology and mathematics, is to reflect upon lived experience. In other words, grasping active inference through autoethnographic research. In this short communication paper, accessing AIT through autoethnography is explained in terms of active inference in existing organizational practice (implicit active inference), new organizational methodologies that are informed by AIT (deliberative active inference), and combining implicit and deliberative active inference. In addition, these autoethnographic options for grasping AIT are related to generative learning. Full article
(This article belongs to the Special Issue Emerging Methods in Active Inference)
Show Figures

Figure 1

Article
Dynamic Expectation Maximization Algorithm for Estimation of Linear Systems with Colored Noise
Entropy 2021, 23(10), 1306; https://doi.org/10.3390/e23101306 - 05 Oct 2021
Cited by 3 | Viewed by 645
Abstract
The free energy principle from neuroscience has recently gained traction as one of the most prominent brain theories that can emulate the brain’s perception and action in a bio-inspired manner. This renders the theory with the potential to hold the key for general [...] Read more.
The free energy principle from neuroscience has recently gained traction as one of the most prominent brain theories that can emulate the brain’s perception and action in a bio-inspired manner. This renders the theory with the potential to hold the key for general artificial intelligence. Leveraging this potential, this paper aims to bridge the gap between neuroscience and robotics by reformulating an FEP-based inference scheme—Dynamic Expectation Maximization—into an algorithm that can perform simultaneous state, input, parameter, and noise hyperparameter estimation of any stable linear state space system subjected to colored noises. The resulting estimator was proved to be of the form of an augmented coupled linear estimator. Using this mathematical formulation, we proved that the estimation steps have theoretical guarantees of convergence. The algorithm was rigorously tested in simulation on a wide variety of linear systems with colored noises. The paper concludes by demonstrating the superior performance of DEM for parameter estimation under colored noise in simulation, when compared to the state-of-the-art estimators like Sub Space method, Prediction Error Minimization (PEM), and Expectation Maximization (EM) algorithm. These results contribute to the applicability of DEM as a robust learning algorithm for safe robotic applications. Full article
(This article belongs to the Special Issue Emerging Methods in Active Inference)
Show Figures

Figure 1

Review

Jump to: Research

Review
The Free Energy Principle for Perception and Action: A Deep Learning Perspective
Entropy 2022, 24(2), 301; https://doi.org/10.3390/e24020301 - 21 Feb 2022
Viewed by 1323
Abstract
The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states of the world, i.e., they minimize their free energy. Under this principle, biological agents learn a [...] Read more.
The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states of the world, i.e., they minimize their free energy. Under this principle, biological agents learn a generative model of the world and plan actions in the future that will maintain the agent in an homeostatic state that satisfies its preferences. This framework lends itself to being realized in silico, as it comprehends important aspects that make it computationally affordable, such as variational inference and amortized planning. In this work, we investigate the tool of deep learning to design and realize artificial agents based on active inference, presenting a deep-learning oriented presentation of the free energy principle, surveying works that are relevant in both machine learning and active inference areas, and discussing the design choices that are involved in the implementation process. This manuscript probes newer perspectives for the active inference framework, grounding its theoretical aspects into more pragmatic affairs, offering a practical guide to active inference newcomers and a starting point for deep learning practitioners that would like to investigate implementations of the free energy principle. Full article
(This article belongs to the Special Issue Emerging Methods in Active Inference)
Show Figures

Figure 1

Back to TopTop