An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity

By James C. R. Whittington, Rafal Bogacz. 2017

368 citations recorded by the source corpus.

Abstract To efficiently learn from feedback, cortical networks need to update synaptic weights on multiple levels of cortical hierarchy. An effective and well-known algorithm for computing such changes in synaptic weights is the error backpropagation algorithm. However, in this algorithm, the change in synaptic weights is a complex function of weights and activities of neurons not directly connected with the synapse being modified, whereas the changes in biological synapses are determined only by the activity of presynaptic and postsynaptic neurons. Several models have been proposed that approximate the backpropagation algorithm with local synaptic plasticity, but these models require complex external control over the network or relatively complex plasticity rules. Here we show that a network developed in the predictive coding framework can efficiently perform supervised learning fully autonomously, employing only simple local Hebbian plasticity. Furthermore, for certain parameters, the weight change in the predictive coding model converges to that of the backpropagation algorithm. This suggests that it is possible for cortical networks with simple Hebbian synaptic plasticity to implement efficient learning algorithms in which synapses in areas on multiple levels of hierarchy are modified to minimize the error on the output.

Subfields: Cognitive Neuroscience, Electrical and Electronic Engineering

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

In Electrical and Electronic Engineering

Citations in the corpus

Continual Learning via Local Module Composition (2021, background): “the number of tasks; (iii) systematic [8] and out-of-distribution (OOD) generalization [18] through knowledge recombination; and (iv) biological plausibility [91, 90, 96].”
Dendritic cortical microcircuits approximate the backpropagation algorithm (2018, background): “Interestingly, recent work has shown that backprop can be mapped onto a predictive coding network architecture (Whittington and Bogacz, 2017), related to the general framework introduced by LeCun (1988).”
Unsupervised learning by competing hidden units (2018, background): “These currents define the dynamics [8] that lead to the steady-state activations of the hidden units.”
Meta-Learning Update Rules for Unsupervised Representation Learning (2018, background): “This has the added beneﬁt that it makes the weight updates more similar to synaptic updates in biological neurons, which depend almost exclusively on local pre-and post-synaptic neuronal activity (Whittington and Bogacz, 2017).”
Training Neural Networks with Local Error Signals (2019, background): “…for error-driven learning have so far focused on how to transport the error back to hidden layers (Lillicrap et al., 2014; Nøkland, 2016), or how to transport a target back to hidden layers (Xie & Seung, 2003; Bengio, 2014; Lee et al., 2015b; Scellier & Bengio, 2017; Whittington & Bogacz, 2017).”
Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding (2018, background): “…has been made toward credit-assignment mechanisms that are functionally equivalent to back-propagation (Lee et al., 2014; Scellier & Bengio, 2016; Whittington & Bogacz, 2017), it remains very unclear how the equivalent of back-propagation through time, used to train recurrent neural networks…”
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures (2018, background): “…as Contrastive Hebbian Learning [24], and Generalized Recirculation [26] – use top-down feedback connections to inﬂuence neural activity , and differences in feedfoward-driven and feedback-driven activities (or products of activities) to locally approximate gradients [1, 31, 26, 39, 4, 36, 38].”
Neuroscience-Inspired Artificial Intelligence. (2017, background): “, continuous Hopfield networks) (Scellier and Bengio, 2016; Whittington and Bogacz, 2017)—models that have strong connections to theoretical neuroscience ideas about predictive coding (Bastos et al.”
If deep learning is the answer, what is the question? (2020, background): “Other learning principles such as contrastive Hebbian learning 72 or predictive coding 75 , which involve feedback connectivity, might predict different distributions and timings of activity changes across layers.”
Theories of Error Back-Propagation in the Brain (2019, methodology): “…is a diversity of ideas on how the back-propagation algorithm may be approximated in the brain [31 – 36]; however, we review the principles behind a set of related models [11,13,14,37] that have substantial connections with biological data while closely paralleling the back-propagation algorithm.”