IWAI 2021

2nd International Workshop
on Active Inference

13 September 2021 - virtually

In Conjunction with ECML/PKDD 2021

The 2nd International Workshop on Active Inference wants to bring together researchers on active inference as well as related research fields in order to discuss current trends, novel results, (real-world) applications, to what extent active inference can be used in modern machine learning settings, such as deep learning, unifying the latest psychological and neurological insights and how it can be used in understanding action, optimization and choice.

Active inference is a theory of behaviour and learning that originated in neuroscience (Friston et al., 2006). The basic assumption is that intelligent agents entertain a generative model of their environment, and their central objective is to minimize a tractable upper bound on the surprise of sensory observations, known as variational free energy. The agents do so either by updating their generative model, so that it becomes better at explaining observations (i.e. learning), or by inferring policies that will resolve their surprise (i.e. acting), for example by moving towards prior, preferred states, or by moving towards less ambiguous states (Friston et al., 2017).

In the field of machine learning, the definition of free energy is also known as the (negative) evidence lower bound (ELBO) in variational Bayesian methods. In deep learning, this has become a popular method to build generative models of complex data using the variational autoencoder framework (Kingma et al., 2014, Rezende et al., 2014). For that reason, active inference has connections with the currently popular domain of reinforcement learning and intrinsic motivation (Friston et al., 2009). In the field of complexity economy, the free energy principle is used to temper rational choice theory reformulating how agents optimize (Morten Henriksen, 2020).

Programme

The workshop will take place virtually September 13th, in conjunction with ECML/PKDD 2021. Download the full schedule here.

Keynotes
Responsive image

Deep active inference agents using Monte-Carlo methods
Zafeirios Fountas


Responsive image

Markov blankets in the brain: how the situatedness in the environment is reflected in neural patterns?
Inês Hipólito


Accepted presentations

Active Inference for Stochastic Control
Aswin Paul, Noor Sajid, Manoj Gopalkrishnan and Adeel Razi
[Paper]

Towards Stochastic Fault-tolerant Control using Precision Learning and Active Inference
Mohamed Baioumy, Corrado Pezzato, Carlos Hernández Corbato, Nick Hawes and Riccardo Ferrari
[Paper]

On the Convergence of DEM’s Linear Parameter Estimator
Ajith Anil Meera and Martijn Wisse
[Paper]

Disentangling what and where for 3D object-centric representations through active inference
Toon Van de Maele, Tim Verbelen, Ozan Catal and Bart Dhoedt
[Paper]

Rule learning through active inductive inference
Tore Erdmann and Christoph Mathys
[Paper]

Interpreting Physical Systems as Bayesian Reasoners
Nathaniel Virgo, Martin Biehl and Simon McGregor
[Paper]

Blankets All the Way Up - The Economics of Active Inference
Morten Henriksen
[Paper]

Filtered States: Active Inference, Social Media and Mental Health
Mark Miller and Ben White
[Paper]

Ideas Worth Spreading: A Free Energy Proposal For Cumulative Cultural Dynamics
Natalie Kastel and Casper Hesp
[Paper]

Dream To Explore: 5-HT2a as adaptive temperature parameter for sophisticated affective inference
Adam Safron and Zahra Sheikhbahaee
[Paper]

Accepted posters

Inferring in Circles: Active Inference in Continuous State Space using Hierarchical Gaussian Filtering of Sufficient Statistics
Peter Thestrup Waade, Nace Mikus and Christoph Mathys
[Paper]

On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference
Mohamed Baioumy, Bruno Lacerda, Paul Duckworth and Nick Hawes
[Paper]

Habitual and Reflective Control in Hierarchical Predictive Coding
Paul Kinghorn, Beren Millidge and Christopher Buckley
[Paper]

Deep active inference for pixel-based discrete control: evaluation on the car racing problem
N.T.A. van Hoeffelen and Pablo Lanillos
[Paper]

Robot Localization and Navigation through Predictive Processing using LiDAR
Daniel Burghardt and Pablo Lanillos
[Paper]

Sensorimotor Visual Perception on Embodied System Using Free Energy Principle
Kanako Esaki, Tadayuki Matsumura, Kiyoto Ito and Hiroyuki Mizuno
[Paper]

Active Inference & Behavior Engineering for Teams
Alexander Vyatkin, Ivan Metelkin, Alexandra Mikhailova, Rj Cordes and Daniel Friedman

Call for papers

Papers on all subjects and applications of active inference and related research areas are welcome. Topics of interest include (but are not limited to):

Important dates

Abstract Submission Deadline: June 9th, 2021
Paper Submission Deadline: June 23rd, 2021 July 11th, 2021
Acceptance Notification: July 28th, 2021 August 13th, 2021
Camera Ready Submission Deadline: September 1st, 2021
Workshop Date: September 13th, 2021

Paper submissions

We welcome submissions of papers with up to 8 printed pages (excluding references) in LNCS format (click here for details). Submissions will be evaluated according to their originality and relevance to the workshop, and should have an abstract of 60-100 words. Contributions should be in PDF format and submitted via Easychair (click here).

In accordance with the main conference, will apply a double-blind review process (see also the double-blind reviewing process section below for further details). All papers need to be anonymized in the best of efforts. It is allowed to have a (non-anonymous) online pre-print. Reviewers will be asked not to search for them.

Registration

The workshop registrations will be handled by ECML/PKDD 2021 (click here). At least one author of each accepted paper should register for the conference.

Keep in mind: the early registration deadline for ECML/PKDD is August 18th, 2021.

Organisers

Christopher Buckley, University of Sussex, United Kingdom
Daniela Cialfi, University of Chieti-Pescara, Italy
Pablo Lanillos, Donders Institute for Brain, Cognition and Behaviour, Netherlands
Maxwell Ramstead, McGill University, Canada
Tim Verbelen, Ghent University - imec, Belgium

Programme committee

Mel Andrews, University of Cincinnati, USA
Glen Berseth, University of California Berkeley, USA
Christopher Buckley, University of Sussex, United Kingdom
Daniela Cialfi, University of Chieti-Pescara, Italy
Cedric De Boom, Ghent University - imec, Belgium
Karl Friston, University College London, United Kingdom
Casper Hesp, University of Amsterdam, Netherlands
Inês Hipólito, Humboldt Universitat zu Berlin, Germany
Natalie Kastel, Univeristy of Amsterdam, Netherlands
Pablo Lanillos, Donders Institute for Brain, Cognition and Behaviour, Netherlands
Christoph Mathys, Aarhus University, Denmark
Mark Miller, Hokkaido University, Japan
Alvaro Ovalle, Queen Mary University of London, United Kingdom
Ayca Ozcelikkale, Uppsala University, Sweden
Maxwell Ramstead, McGill University, Canada
Noor Sajid, University College London, United Kingdom
Kai Ueltzhöffer, Heidelberg University, Germany
Tim Verbelen, Ghent University - imec, Belgium
Martijn Wisse, Delft University of Technology, Netherlands

Previous editions

2020 - Ghent (virtual)

References

Karl Friston, James Kilner, Lee Harrison. A free energy principle for the brain. Journal of Physiology-Paris, Volume 100, Issues 1–3, 2006.

Karl J. Friston, Jean Daunizeau, and Stefan J. Kiebel. Reinforcement Learning or Active Inference? PLoS ONE, 4(7), 2009.

Karl J. Friston, Marco Lin, Christopher D. Frith, Giovanni Pezzulo, J. Allan Hobson, and Sasha Ondobaka. Active Inference, Curiosity and Insight. Neural Computation, 29(10): 2633–2683, 2017.

Diederik P. Kingma and Max Welling. Auto-encoding variational bayes. 2nd International Conference on Learning Representations, 2014.

Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. Stochastic backpropagation and approximate inference in deep generative models. 31st International Conference on International Conference on Machine Learning, 2014.

Henriksen, M. Variational Free energy and Economics Optimizing With Biases and Bounded Rationality. Frontier in Psychology, 11:549187, 2020.