1
|
Paul A, Isomura T, Razi A. On Predictive Planning and Counterfactual Learning in Active Inference. ENTROPY (BASEL, SWITZERLAND) 2024; 26:484. [PMID: 38920492 PMCID: PMC11202763 DOI: 10.3390/e26060484] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/23/2024] [Revised: 05/27/2024] [Accepted: 05/28/2024] [Indexed: 06/27/2024]
Abstract
Given the rapid advancement of artificial intelligence, understanding the foundations of intelligent behaviour is increasingly important. Active inference, regarded as a general theory of behaviour, offers a principled approach to probing the basis of sophistication in planning and decision-making. This paper examines two decision-making schemes in active inference based on "planning" and "learning from experience". Furthermore, we also introduce a mixed model that navigates the data complexity trade-off between these strategies, leveraging the strengths of both to facilitate balanced decision-making. We evaluate our proposed model in a challenging grid-world scenario that requires adaptability from the agent. Additionally, our model provides the opportunity to analyse the evolution of various parameters, offering valuable insights and contributing to an explainable framework for intelligent decision-making.
Collapse
Affiliation(s)
- Aswin Paul
- Turner Institute for Brain and Mental Health, School of Psychological Sciences, Monash University, Clayton 3800, Australia;
- IITB-Monash Research Academy, Mumbai 400076, India
- Department of Electrical Engineering, IIT Bombay, Mumbai 400076 , India
| | - Takuya Isomura
- Brain Intelligence Theory Unit, RIKEN Center for Brain Science, Wako, Saitama 351-0106, Japan;
| | - Adeel Razi
- Turner Institute for Brain and Mental Health, School of Psychological Sciences, Monash University, Clayton 3800, Australia;
- Wellcome Trust Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK
- CIFAR Azrieli Global Scholars Program, CIFAR, Toronto, ON M5G 1M1, Canada
| |
Collapse
|
2
|
Hodson R, Mehta M, Smith R. The empirical status of predictive coding and active inference. Neurosci Biobehav Rev 2024; 157:105473. [PMID: 38030100 DOI: 10.1016/j.neubiorev.2023.105473] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2023] [Revised: 10/27/2023] [Accepted: 11/16/2023] [Indexed: 12/01/2023]
Abstract
Research on predictive processing models has focused largely on two specific algorithmic theories: Predictive Coding for perception and Active Inference for decision-making. While these interconnected theories possess broad explanatory potential, they have only recently begun to receive direct empirical evaluation. Here, we review recent studies of Predictive Coding and Active Inference with a focus on evaluating the degree to which they are empirically supported. For Predictive Coding, we find that existing empirical evidence offers modest support. However, some positive results can also be explained by alternative feedforward (e.g., feature detection-based) models. For Active Inference, most empirical studies have focused on fitting these models to behavior as a means of identifying and explaining individual or group differences. While Active Inference models tend to explain behavioral data reasonably well, there has not been a focus on testing empirical validity of active inference theory per se, which would require formal comparison to other models (e.g., non-Bayesian or model-free reinforcement learning models). This review suggests that, while promising, a number of specific research directions are still necessary to evaluate the empirical adequacy and explanatory power of these algorithms.
Collapse
Affiliation(s)
| | | | - Ryan Smith
- Laureate Institute for Brain Research, USA.
| |
Collapse
|
3
|
Hipólito I, Mago J, Rosas FE, Carhart-Harris R. Pattern breaking: a complex systems approach to psychedelic medicine. Neurosci Conscious 2023; 2023:niad017. [PMID: 37424966 PMCID: PMC10325487 DOI: 10.1093/nc/niad017] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2022] [Revised: 05/19/2023] [Accepted: 06/08/2023] [Indexed: 07/11/2023] Open
Abstract
Recent research has demonstrated the potential of psychedelic therapy for mental health care. However, the psychological experience underlying its therapeutic effects remains poorly understood. This paper proposes a framework that suggests psychedelics act as destabilizers, both psychologically and neurophysiologically. Drawing on the 'entropic brain' hypothesis and the 'RElaxed Beliefs Under pSychedelics' model, this paper focuses on the richness of psychological experience. Through a complex systems theory perspective, we suggest that psychedelics destabilize fixed points or attractors, breaking reinforced patterns of thinking and behaving. Our approach explains how psychedelic-induced increases in brain entropy destabilize neurophysiological set points and lead to new conceptualizations of psychedelic psychotherapy. These insights have important implications for risk mitigation and treatment optimization in psychedelic medicine, both during the peak psychedelic experience and during the subacute period of potential recovery.
Collapse
Affiliation(s)
- Inês Hipólito
- Berlin School of Mind and Brain, Humboldt-Universität zu Berlin, Berlin 10117, Germany
- Department of Philosophy, Macquarie University, New South Wales 2109, Australia
| | - Jonas Mago
- Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, United Kingdom
- Integrative Program in Neuroscience, McGill University, Montreal, Quebec QC H3A, Canada
| | - Fernando E Rosas
- Department of Brain Sciences, Centre for Psychedelic Research, Imperial College London, London SW7 2BX, United Kingdom
- Centre for Complexity Science, Imperial College London, London SW7 2BX, United Kingdom
- Data Science Institute, Imperial College London, London SW7 2BX, United Kingdom
- Department of Informatics, University of Sussex, Brighton BN1 9RH, United Kingdom
- Centre for Eudaimonia and Human Flourishing, University of Oxford, Oxford OX3 9BX, United Kingdom
| | - Robin Carhart-Harris
- Department of Brain Sciences, Centre for Psychedelic Research, Imperial College London, London SW7 2BX, United Kingdom
- Psychedelics Division, University of California San Francisco, San Francisco, CA 92521, United States
| |
Collapse
|
4
|
Ramstead MJD, Sakthivadivel DAR, Heins C, Koudahl M, Millidge B, Da Costa L, Klein B, Friston KJ. On Bayesian mechanics: a physics of and by beliefs. Interface Focus 2023; 13:20220029. [PMID: 37213925 PMCID: PMC10198254 DOI: 10.1098/rsfs.2022.0029] [Citation(s) in RCA: 19] [Impact Index Per Article: 19.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Accepted: 01/17/2023] [Indexed: 05/23/2023] Open
Abstract
The aim of this paper is to introduce a field of study that has emerged over the last decade, called Bayesian mechanics. Bayesian mechanics is a probabilistic mechanics, comprising tools that enable us to model systems endowed with a particular partition (i.e. into particles), where the internal states (or the trajectories of internal states) of a particular system encode the parameters of beliefs about external states (or their trajectories). These tools allow us to write down mechanical theories for systems that look as if they are estimating posterior probability distributions over the causes of their sensory states. This provides a formal language for modelling the constraints, forces, potentials and other quantities determining the dynamics of such systems, especially as they entail dynamics on a space of beliefs (i.e. on a statistical manifold). Here, we will review the state of the art in the literature on the free energy principle, distinguishing between three ways in which Bayesian mechanics has been applied to particular systems (i.e. path-tracking, mode-tracking and mode-matching). We go on to examine a duality between the free energy principle and the constrained maximum entropy principle, both of which lie at the heart of Bayesian mechanics, and discuss its implications.
Collapse
Affiliation(s)
- Maxwell J. D. Ramstead
- VERSES Research Lab, Los Angeles, CA 90016, USA
- Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK
| | - Dalton A. R. Sakthivadivel
- VERSES Research Lab, Los Angeles, CA 90016, USA
- Department of Mathematics, Stony Brook University, Stony Brook, NY, USA
- Department of Physics and Astronomy, Stony Brook University, Stony Brook, NY, USA
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, NY, USA
| | - Conor Heins
- VERSES Research Lab, Los Angeles, CA 90016, USA
- Department of Collective Behaviour, Max Planck Institute of Animal Behavior, 78464 Konstanz, Germany
- Department of Biology, University of Konstanz, 78464 Konstanz, Germany
- Centre for the Advanced Study of Collective Behaviour, University of Konstanz, 78464 Konstanz, Germany
| | - Magnus Koudahl
- VERSES Research Lab, Los Angeles, CA 90016, USA
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Beren Millidge
- VERSES Research Lab, Los Angeles, CA 90016, USA
- Brain Network Dynamics Unit, University of Oxford, Oxford, UK
| | - Lancelot Da Costa
- Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK
- Department of Mathematics, Imperial College London, London SW7 2AZ, UK
| | - Brennan Klein
- VERSES Research Lab, Los Angeles, CA 90016, USA
- Network Science Institute, Northeastern University, Boston, MA, USA
| | - Karl J. Friston
- VERSES Research Lab, Los Angeles, CA 90016, USA
- Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK
| |
Collapse
|
5
|
Konaka Y, Naoki H. Decoding reward-curiosity conflict in decision-making from irrational behaviors. NATURE COMPUTATIONAL SCIENCE 2023; 3:418-432. [PMID: 38177842 PMCID: PMC10768639 DOI: 10.1038/s43588-023-00439-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/21/2022] [Accepted: 03/29/2023] [Indexed: 01/06/2024]
Abstract
Humans and animals are not always rational. They not only rationally exploit rewards but also explore an environment owing to their curiosity. However, the mechanism of such curiosity-driven irrational behavior is largely unknown. Here, we developed a decision-making model for a two-choice task based on the free energy principle, which is a theory integrating recognition and action selection. The model describes irrational behaviors depending on the curiosity level. We also proposed a machine learning method to decode temporal curiosity from behavioral data. By applying it to rat behavioral data, we found that the rat had negative curiosity, reflecting conservative selection sticking to more certain options and that the level of curiosity was upregulated by the expected future information obtained from an uncertain environment. Our decoding approach can be a fundamental tool for identifying the neural basis for reward-curiosity conflicts. Furthermore, it could be effective in diagnosing mental disorders.
Collapse
Affiliation(s)
- Yuki Konaka
- Laboratory of Data-Driven Biology, Graduate School of Integrated Sciences for Life, Hiroshima University, Hiroshima, Japan
| | - Honda Naoki
- Laboratory of Data-Driven Biology, Graduate School of Integrated Sciences for Life, Hiroshima University, Hiroshima, Japan.
- Kansei-Brain Informatics Group, Center for Brain, Mind and Kansei Sciences Research, Hiroshima University, Hiroshima, Japan.
- Theoretical Biology Research Group, Exploratory Research Center on Life and Living Systems, National Institutes of Natural Sciences, Okazaki, Japan.
- Laboratory of Theoretical Biology, Graduate School of Biostudies, Kyoto University, Kyoto, Japan.
| |
Collapse
|
6
|
Branching time active inference: Empirical study and complexity class analysis. Neural Netw 2022; 152:450-466. [DOI: 10.1016/j.neunet.2022.05.010] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2021] [Revised: 03/26/2022] [Accepted: 05/10/2022] [Indexed: 12/25/2022]
|
7
|
Kiverstein J, Kirchhoff MD, Froese T. The Problem of Meaning: The Free Energy Principle and Artificial Agency. Front Neurorobot 2022; 16:844773. [PMID: 35812784 PMCID: PMC9260223 DOI: 10.3389/fnbot.2022.844773] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2021] [Accepted: 05/17/2022] [Indexed: 12/13/2022] Open
Abstract
Biological agents can act in ways that express a sensitivity to context-dependent relevance. So far it has proven difficult to engineer this capacity for context-dependent sensitivity to relevance in artificial agents. We give this problem the label the "problem of meaning". The problem of meaning could be circumvented if artificial intelligence researchers were to design agents based on the assumption of the continuity of life and mind. In this paper, we focus on the proposal made by enactive cognitive scientists to design artificial agents that possess sensorimotor autonomy-stable, self-sustaining patterns of sensorimotor interaction that can ground values, norms and goals necessary for encountering a meaningful environment. More specifically, we consider whether the Free Energy Principle (FEP) can provide formal tools for modeling sensorimotor autonomy. There is currently no consensus on how to understand the relationship between enactive cognitive science and the FEP. However, a number of recent papers have argued that the two frameworks are fundamentally incompatible. Some argue that biological systems exhibit historical path-dependent learning that is absent from systems that minimize free energy. Others have argued that a free energy minimizing system would fail to satisfy a key condition for sensorimotor agency referred to as "interactional asymmetry". These critics question the claim we defend in this paper that the FEP can be used to formally model autonomy and adaptivity. We will argue it is too soon to conclude that the two frameworks are incompatible. There are undeniable conceptual differences between the two frameworks but in our view each has something important and necessary to offer. The FEP needs enactive cognitive science for the solution it provides to the problem of meaning. Enactive cognitive science needs the FEP to formally model the properties it argues to be constitutive of agency. Our conclusion will be that active inference models based on the FEP provides a way by which scientists can think about how to address the problems of engineering autonomy and adaptivity in artificial agents in formal terms. In the end engaging more closely with this formalism and its further developments will benefit those working within the enactive framework.
Collapse
Affiliation(s)
- Julian Kiverstein
- Academic Medical Center, Amsterdam, Netherlands
- Amsterdam Brain and Cognition, University of Amsterdam, Amsterdam, Netherlands
| | - Michael D. Kirchhoff
- Faculty of Arts, Social Sciences, and Humanities, School of Liberal Arts, University of Wollongong, Wollongong, NSW, Australia
| | - Tom Froese
- Embodied Cognitive Science Unit, Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan
| |
Collapse
|
8
|
Champion T, Da Costa L, Bowman H, Grześ M. Branching Time Active Inference: The theory and its generality. Neural Netw 2022; 151:295-316. [PMID: 35468491 DOI: 10.1016/j.neunet.2022.03.036] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2021] [Revised: 03/25/2022] [Accepted: 03/28/2022] [Indexed: 12/01/2022]
Abstract
Over the last 10 to 15 years, active inference has helped to explain various brain mechanisms from habit formation to dopaminergic discharge and even modelling curiosity. However, the current implementations suffer from an exponential (space and time) complexity class when computing the prior over all the possible policies up to the time-horizon. Fountas et al. (2020) used Monte Carlo tree search to address this problem, leading to impressive results in two different tasks. In this paper, we present an alternative framework that aims to unify tree search and active inference by casting planning as a structure learning problem. Two tree search algorithms are then presented. The first propagates the expected free energy forward in time (i.e., towards the leaves), while the second propagates it backward (i.e., towards the root). Then, we demonstrate that forward and backward propagations are related to active inference and sophisticated inference, respectively, thereby clarifying the differences between those two planning strategies.
Collapse
Affiliation(s)
- Théophile Champion
- University of Kent, School of Computing, Canterbury CT2 7NZ, United Kingdom.
| | - Lancelot Da Costa
- Imperial College London, Department of Mathematics, London SW7 2AZ, United Kingdom; Wellcome Centre for Human Neuroimaging, University College London, London, WC1N 3AR, United Kingdom.
| | - Howard Bowman
- University of Birmingham, School of Psychology, Birmingham B15 2TT, United Kingdom; University of Kent, School of Computing, Canterbury CT2 7NZ, United Kingdom.
| | - Marek Grześ
- University of Kent, School of Computing, Canterbury CT2 7NZ, United Kingdom.
| |
Collapse
|
9
|
van de Laar T, Koudahl M, van Erp B, de Vries B. Active Inference and Epistemic Value in Graphical Models. Front Robot AI 2022; 9:794464. [PMID: 35462780 PMCID: PMC9019474 DOI: 10.3389/frobt.2022.794464] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2021] [Accepted: 01/27/2022] [Indexed: 11/29/2022] Open
Abstract
The Free Energy Principle (FEP) postulates that biological agents perceive and interact with their environment in order to minimize a Variational Free Energy (VFE) with respect to a generative model of their environment. The inference of a policy (future control sequence) according to the FEP is known as Active Inference (AIF). The AIF literature describes multiple VFE objectives for policy planning that lead to epistemic (information-seeking) behavior. However, most objectives have limited modeling flexibility. This paper approaches epistemic behavior from a constrained Bethe Free Energy (CBFE) perspective. Crucially, variational optimization of the CBFE can be expressed in terms of message passing on free-form generative models. The key intuition behind the CBFE is that we impose a point-mass constraint on predicted outcomes, which explicitly encodes the assumption that the agent will make observations in the future. We interpret the CBFE objective in terms of its constituent behavioral drives. We then illustrate resulting behavior of the CBFE by planning and interacting with a simulated T-maze environment. Simulations for the T-maze task illustrate how the CBFE agent exhibits an epistemic drive, and actively plans ahead to account for the impact of predicted outcomes. Compared to an EFE agent, the CBFE agent incurs expected reward in significantly more environmental scenarios. We conclude that CBFE optimization by message passing suggests a general mechanism for epistemic-aware AIF in free-form generative models.
Collapse
Affiliation(s)
- Thijs van de Laar
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
- *Correspondence: Thijs van de Laar,
| | - Magnus Koudahl
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
- Nested Minds Network Ltd., Liverpool, United Kingdom
| | - Bart van Erp
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
| | - Bert de Vries
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
- GN Hearing Benelux BV, Eindhoven, Netherlands
| |
Collapse
|
10
|
Smith R, Friston KJ, Whyte CJ. A step-by-step tutorial on active inference and its application to empirical data. JOURNAL OF MATHEMATICAL PSYCHOLOGY 2022; 107:102632. [PMID: 35340847 PMCID: PMC8956124 DOI: 10.1016/j.jmp.2021.102632] [Citation(s) in RCA: 37] [Impact Index Per Article: 18.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/26/2023]
Abstract
The active inference framework, and in particular its recent formulation as a partially observable Markov decision process (POMDP), has gained increasing popularity in recent years as a useful approach for modeling neurocognitive processes. This framework is highly general and flexible in its ability to be customized to model any cognitive process, as well as simulate predicted neuronal responses based on its accompanying neural process theory. It also affords both simulation experiments for proof of principle and behavioral modeling for empirical studies. However, there are limited resources that explain how to build and run these models in practice, which limits their widespread use. Most introductions assume a technical background in programming, mathematics, and machine learning. In this paper we offer a step-by-step tutorial on how to build POMDPs, run simulations using standard MATLAB routines, and fit these models to empirical data. We assume a minimal background in programming and mathematics, thoroughly explain all equations, and provide exemplar scripts that can be customized for both theoretical and empirical studies. Our goal is to provide the reader with the requisite background knowledge and practical tools to apply active inference to their own research. We also provide optional technical sections and multiple appendices, which offer the interested reader additional technical details. This tutorial should provide the reader with all the tools necessary to use these models and to follow emerging advances in active inference research.
Collapse
Affiliation(s)
- Ryan Smith
- Laureate Institute for Brain Research, Tulsa, OK, USA
| | - Karl J. Friston
- Wellcome Centre for Human Neuroimaging, Institute of Neurology, University College London, WC1N 3AR, UK
| | | |
Collapse
|
11
|
Albarracin M, Demekas D, Ramstead MJD, Heins C. Epistemic Communities under Active Inference. ENTROPY (BASEL, SWITZERLAND) 2022; 24:476. [PMID: 35455140 PMCID: PMC9027706 DOI: 10.3390/e24040476] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/04/2022] [Revised: 03/11/2022] [Accepted: 03/24/2022] [Indexed: 02/04/2023]
Abstract
The spread of ideas is a fundamental concern of today's news ecology. Understanding the dynamics of the spread of information and its co-option by interested parties is of critical importance. Research on this topic has shown that individuals tend to cluster in echo-chambers and are driven by confirmation bias. In this paper, we leverage the active inference framework to provide an in silico model of confirmation bias and its effect on echo-chamber formation. We build a model based on active inference, where agents tend to sample information in order to justify their own view of reality, which eventually leads to them to have a high degree of certainty about their own beliefs. We show that, once agents have reached a certain level of certainty about their beliefs, it becomes very difficult to get them to change their views. This system of self-confirming beliefs is upheld and reinforced by the evolving relationship between an agent's beliefs and observations, which over time will continue to provide evidence for their ingrained ideas about the world. The epistemic communities that are consolidated by these shared beliefs, in turn, tend to produce perceptions of reality that reinforce those shared beliefs. We provide an active inference account of this community formation mechanism. We postulate that agents are driven by the epistemic value that they obtain from sampling or observing the behaviours of other agents. Inspired by digital social networks like Twitter, we build a generative model in which agents generate observable social claims or posts (e.g., 'tweets') while reading the socially observable claims of other agents that lend support to one of two mutually exclusive abstract topics. Agents can choose which other agent they pay attention to at each timestep, and crucially who they attend to and what they choose to read influences their beliefs about the world. Agents also assess their local network's perspective, influencing which kinds of posts they expect to see other agents making. The model was built and simulated using the freely available Python package pymdp. The proposed active inference model can reproduce the formation of echo-chambers over social networks, and gives us insight into the cognitive processes that lead to this phenomenon.
Collapse
Affiliation(s)
- Mahault Albarracin
- Department of Cognitive Computing, Université du Québec a Montreal, Montreal, QC H2K 4M1, Canada;
- VERSES Labs, Los Angeles, CA 90016, USA;
| | - Daphne Demekas
- Department of Computing, Imperial College London, London SW7 5NH, UK;
| | - Maxwell J. D. Ramstead
- VERSES Labs, Los Angeles, CA 90016, USA;
- Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK
| | - Conor Heins
- VERSES Labs, Los Angeles, CA 90016, USA;
- Department of Collective Behaviour, Max Planck Institute of Animal Behaviour, 78315 Radolfzell am Bodensee, Germany
- Centre for the Advanced Study of Collective Behaviour, University of Konstanz, 78464 Konstanz, Germany
- Department of Biology, University of Konstanz, 78457 Konstanz, Germany
| |
Collapse
|
12
|
Mazzaglia P, Verbelen T, Çatal O, Dhoedt B. The Free Energy Principle for Perception and Action: A Deep Learning Perspective. ENTROPY (BASEL, SWITZERLAND) 2022; 24:301. [PMID: 35205595 PMCID: PMC8871280 DOI: 10.3390/e24020301] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/21/2021] [Revised: 02/14/2022] [Accepted: 02/15/2022] [Indexed: 02/05/2023]
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 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.
Collapse
Affiliation(s)
- Pietro Mazzaglia
- IDLab, Ghent University, 9052 Gent, Belgium; (T.V.); (O.Ç.); (B.D.)
| | | | | | | |
Collapse
|
13
|
Sennesh E, Theriault J, Brooks D, van de Meent JW, Barrett LF, Quigley KS. Interoception as modeling, allostasis as control. Biol Psychol 2022; 167:108242. [PMID: 34942287 PMCID: PMC9270659 DOI: 10.1016/j.biopsycho.2021.108242] [Citation(s) in RCA: 36] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2021] [Revised: 12/13/2021] [Accepted: 12/14/2021] [Indexed: 01/09/2023]
Abstract
The brain regulates the body by anticipating its needs and attempting to meet them before they arise - a process called allostasis. Allostasis requires a model of the changing sensory conditions within the body, a process called interoception. In this paper, we examine how interoception may provide performance feedback for allostasis. We suggest studying allostasis in terms of control theory, reviewing control theory's applications to related issues in physiology, motor control, and decision making. We synthesize these by relating them to the important properties of allostatic regulation as a control problem. We then sketch a novel formalism for how the brain might perform allostatic control of the viscera by analogy to skeletomotor control, including a mathematical view on how interoception acts as performance feedback for allostasis. Finally, we suggest ways to test implications of our hypotheses.
Collapse
Affiliation(s)
- Eli Sennesh
- Northeastern University, Boston, MA , United States.
| | | | - Dana Brooks
- Northeastern University, Boston, MA , United States
| | | | | | | |
Collapse
|
14
|
Koudahl MT, Kouw WM, de Vries B. On Epistemics in Expected Free Energy for Linear Gaussian State Space Models. ENTROPY 2021; 23:e23121565. [PMID: 34945871 PMCID: PMC8700494 DOI: 10.3390/e23121565] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Revised: 11/19/2021] [Accepted: 11/23/2021] [Indexed: 01/20/2023]
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 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.
Collapse
Affiliation(s)
- Magnus T. Koudahl
- Department of Electrical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands; (W.M.K.); (B.d.V.)
- Correspondence:
| | - Wouter M. Kouw
- Department of Electrical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands; (W.M.K.); (B.d.V.)
| | - Bert de Vries
- Department of Electrical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands; (W.M.K.); (B.d.V.)
- GN Hearing, JF Kennedylaan 2, 5612 AB Eindhoven, The Netherlands
| |
Collapse
|
15
|
Fox S. Future-Proofing Startups: Stress Management Principles Based on Adaptive Calibration Model and Active Inference Theory. ENTROPY 2021; 23:e23091155. [PMID: 34573780 PMCID: PMC8468633 DOI: 10.3390/e23091155] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/14/2021] [Revised: 08/30/2021] [Accepted: 08/31/2021] [Indexed: 12/12/2022]
Abstract
In this paper, the Adaptive Calibration Model (ACM) and Active Inference Theory (AIT) are related to future-proofing startups. ACM encompasses the allocation of energy by the stress response system to alternative options for action, depending upon individuals’ life histories and changing external contexts. More broadly, within AIT, it is posited that humans survive by taking action to align their internal generative models with sensory inputs from external states. The first contribution of the paper is to address the need for future-proofing methods for startups by providing eight stress management principles based on ACM and AIT. Future-proofing methods are needed because, typically, nine out of ten startups do not survive. A second contribution is to relate ACM and AIT to startup life cycle stages. The third contribution is to provide practical examples that show the broader relevance ACM and AIT to organizational practice. These contributions go beyond previous literature concerned with entrepreneurial stress and organizational stress. In particular, rather than focusing on particular stressors, this paper is focused on the recalibrating/updating of startups’ stress responsivity patterns in relation to changes in the internal state of the startup and/or changes in the external state. Overall, the paper makes a contribution to relating physics of life constructs concerned with energy, action and ecological fitness to human organizations.
Collapse
Affiliation(s)
- Stephen Fox
- VTT Technical Research Centre of Finland, FI-02150 Espoo, Finland
| |
Collapse
|
16
|
Champion T, Grześ M, Bowman H. Realizing Active Inference in Variational Message Passing: The Outcome-Blind Certainty Seeker. Neural Comput 2021; 33:2762-2826. [PMID: 34280302 DOI: 10.1162/neco_a_01422] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2021] [Accepted: 04/20/2021] [Indexed: 11/04/2022]
Abstract
Active inference is a state-of-the-art framework in neuroscience that offers a unified theory of brain function. It is also proposed as a framework for planning in AI. Unfortunately, the complex mathematics required to create new models can impede application of active inference in neuroscience and AI research. This letter addresses this problem by providing a complete mathematical treatment of the active inference framework in discrete time and state spaces and the derivation of the update equations for any new model. We leverage the theoretical connection between active inference and variational message passing as described by John Winn and Christopher M. Bishop in 2005. Since variational message passing is a well-defined methodology for deriving Bayesian belief update equations, this letter opens the door to advanced generative models for active inference. We show that using a fully factorized variational distribution simplifies the expected free energy, which furnishes priors over policies so that agents seek unambiguous states. Finally, we consider future extensions that support deep tree searches for sequential policy optimization based on structure learning and belief propagation.
Collapse
Affiliation(s)
| | - Marek Grześ
- University of Kent, School of Computing, Canterbury CT2 7NZ, U.K.
| | - Howard Bowman
- University of Birmingham, School of Psychology, Birmingham B15 2TT, U.K., and University of Kent, School of Computing, Canterbury CT2 7NZ, U.K.
| |
Collapse
|
17
|
Kim CS. Bayesian mechanics of perceptual inference and motor control in the brain. BIOLOGICAL CYBERNETICS 2021; 115:87-102. [PMID: 33471182 PMCID: PMC7925488 DOI: 10.1007/s00422-021-00859-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/21/2020] [Accepted: 01/06/2021] [Indexed: 06/12/2023]
Abstract
The free energy principle (FEP) in the neurosciences stipulates that all viable agents induce and minimize informational free energy in the brain to fit their environmental niche. In this study, we continue our effort to make the FEP a more physically principled formalism by implementing free energy minimization based on the principle of least action. We build a Bayesian mechanics (BM) by casting the formulation reported in the earlier publication (Kim in Neural Comput 30:2616-2659, 2018, https://doi.org/10.1162/neco_a_01115 ) to considering active inference beyond passive perception. The BM is a neural implementation of variational Bayes under the FEP in continuous time. The resulting BM is provided as an effective Hamilton's equation of motion and subject to the control signal arising from the brain's prediction errors at the proprioceptive level. To demonstrate the utility of our approach, we adopt a simple agent-based model and present a concrete numerical illustration of the brain performing recognition dynamics by integrating BM in neural phase space. Furthermore, we recapitulate the major theoretical architectures in the FEP by comparing our approach with the common state-space formulations.
Collapse
Affiliation(s)
- Chang Sub Kim
- Department of Physics, Chonnam National University, Gwangju, 61186, Republic of Korea.
| |
Collapse
|