A tutorial on the free-energy framework for modelling perception and learning

By Rafal Bogacz. Journal of Mathematical Psychology, 2017

312 citations recorded by the source corpus.

This paper provides an easy to follow tutorial on the free-energy framework for modelling perception developed by Friston, which extends the predictive coding model of Rao and Ballard. These models assume that the sensory cortex infers the most likely values of attributes or features of sensory stimuli from the noisy inputs encoding the stimuli. Remarkably, these models describe how this inference could be implemented in a network of very simple computational elements, suggesting that this inference could be performed by biological networks of neurons. Furthermore, learning about the parameters describing the features and their uncertainty is implemented in these models by simple rules of synaptic plasticity based on Hebbian learning. This tutorial introduces the free-energy framework using very simple examples, and provides step-by-step derivations of the model. It also discusses in more detail how the model could be implemented in biological neural circuits. In particular, it presents an extended version of the model in which the neurons only sum their inputs, and synaptic plasticity only depends on activity of pre-synaptic and post-synaptic neurons.

Subfields: Artificial Intelligence, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/57070167d647bfa23bc5c5895623af13576db66b

How researchers see this paper

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

In Artificial Intelligence

In Cognitive Neuroscience

Citations in the corpus

Theories of Error Back-Propagation in the Brain (2019, background): “The free energy has a particularly nice statistical interpretation, as its negative provides a lower bound on the log probability of predicting the target pattern by the network [70,71] (in case of supervised learning, this .”
The free energy principle for action and perception: A mathematical review (2017, background): “It is possible to pursue the full general case, e.g., see Bogacz (2017) for a nice tutorial on this, but we do not consider this here.”
Vanilla PP for Philosophers: A Primer on Predictive Processing (2017, background): “Explaining this requires a slightly more formal description (here, we will simplify matters; a much more detailed, but still accessible, explanation of the free-energy principle can be found in Bogacz 2015).”
The free energy principle made simpler but not too simple (2022, unknown): “This means that all the above formulations are internally consistent with things like the Bayesian brain hypothesis, evidence accumulation and predictive coding [57,58,77].”
Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction (2018, methodology): “Later, this theory was widely applied in the ﬁeld of neuroscience (Rao and Ballard, 1999; Friston and Kiebel, 2009) and has been also developed as “free energy theory,” which is based on a variational Bayesian method (Friston and Kiebel, 2009; Bogacz, 2017).”
An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity (2017, background): “For simplicity in this letter, we do not consider how are learned (Friston, 2005; Bogacz, 2017), but treat them as fixed parameters.”