The free energy principle for action and perception: A mathematical review

By C. L. Buckley, Chang Sub Kim, Simon McGregor, Anil K. Seth. 2017

363 citations recorded by the source corpus.

The ‘free energy principle’ (FEP) has been suggested to provide a unified theory of the brain, integrating data and theory relating to action, perception, and learning. The theory and implementation of the FEP combines insights from Helmholtzian ‘perception as inference’, machine learning theory, and statistical thermodynamics. Here, we provide a detailed mathematical evaluation of a suggested biologically plausible implementation of the FEP that has been widely used to develop the theory. Our objectives are (i) to describe within a single article the mathematical structure of this implementation of the FEP; (ii) provide a simple but complete agent-based model utilising the FEP and (iii) to disclose the assumption structure of this implementation of the FEP to help elucidate its significance for the brain sciences.

Subfields: Cognitive Neuroscience, Social Psychology, Scaling & Learning Theory, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

1. Germán Kruszewski
2. Tomasz Korbak
3. Ethan Perez
4. C. L. Buckley

In Social Psychology

1. C. L. Buckley

In Probabilistic & Bayesian Methods

1. Germán Kruszewski
2. Hady ElSahar
3. Marc Dymetman
4. Tomasz Korbak
5. Ethan Perez
6. C. L. Buckley

Citations in the corpus

• On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting (2022, background): “The idea of posing control problems as distribution matching has resurfaced numerous times in the RL literature (Kappen et al., 2012; Friston et al., 2010; Levine, 2018; Hafner et al., 2020; Buckley et al., 2017).”
• RL with KL penalties is better viewed as Bayesian inference (2022, background): “More-over, there are frameworks such as active inference (Friston et al., 2010; Buckley et al., 2017) or action and perception as divergence minimisation (Hafner et al., 2020) that further generalise control as inference to a principle of minimising the KL divergence from a probability distribution…”
• The free energy principle made simpler but not too simple (2022, neutral): “Some cardinal examples are summarised in Figure 3; see [57, 58, 5, 59] for some formal accounts of these relationships.”