A Theoretical Framework for Inference and Learning in Predictive Coding Networks

Millidge B
Song Y
Salvatori T
Lukasiewicz T
Bogacz R

This paper analyses a relationship between a model of learning in the brain (called predictive coding), and an algorithm for training artificial neural networks (called target propagation).

Scientific Abstract

Predictive coding (PC) is an influential theory in computational neuroscience, which argues that the cortex forms unsupervised world models by implementing a hierarchical process of prediction error minimization. PC networks (PCNs) are trained in two phases. First, neural activities are updated to optimize the network’s response to external stimuli. Second, synaptic weights are updated to consolidate this change in activity — an algorithm called prospective configuration. While previous work has shown how in various limits, PCNs can be found to approximate backpropagation (BP), recent work has demonstrated that PCNs operating in this standard regime, which does not approximate BP, nevertheless obtain competitive training and generalization performance to BP-trained networks while outperforming them on various tasks. However, little is understood theoretically about the properties and dynamics of PCNs in this regime. In this paper, we provide a comprehensive theoretical analysis of the properties of PCNs trained with prospective configuration. We first derive analytical results concerning the inference equilibrium for PCNs and a previously unknown close connection relationship to target propagation (TP). Secondly, we provide a theoretical analysis of learning in PCNs as a variant of generalized expectation-maximization and use that to prove the convergence of PCNs to critical points of the BP loss function, thus showing that deep PCNs can, in theory, achieve the same generalization performance as BP, while maintaining their unique advantages.

Similarity of algorithms
Similarity between variables from predictive coding, backpropagation and target propagation.
2023. The Eleventh International Conference on Learning Representations
Related Content
Millidge B, Song Y, Salvatori T, Lukasiewicz T, Bogacz R
2023. The Eleventh International Conference on Learning Representations
Salvatori T, Song Y, Yordanov Y, Millidge B, Sha L, Emde C, Xu Z, Bogacz R, Lukasiewicz T
2024. The Twelveth International Conference on Learning Representations
Song Y, Lukasiewicz T, Xu Z, Bogacz R
2020. Adv Neural Inf Process Syst, 33:22566-22579.
Salvatori T, Song Y, Xu Z, Lukasiewicz T, Bogacz R
In Proceedings of the 36th AAAI Conference on Artificial Intelligence‚ AAAI 2022 ‚Vancouver, BC, Canada, February 22--March 1‚ 2022 (Vol. 10177, pp. 507-524). AAAI Press.
Tang M, Salvatori T, Millidge B, Song Y, Lukasiewicz T, Bogacz R

2023. PLoS Comput Biol, 19(4)e1010719.