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

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 synap...

Full description

Saved in:
Bibliographic Details
Published in:Neural computation Vol. 29; no. 5; p. 1229
Main Authors: Whittington, James C R, Bogacz, Rafal
Format: Journal Article
Language:English
Published: United States 01.05.2017
Subjects:
Algorithms
Cerebral Cortex - cytology
Feedback, Physiological - physiology
Humans
Learning
Models, Neurological
Neural Networks, Computer
Neuronal Plasticity - physiology
Neurons - physiology
ISSN:1530-888X, 1530-888X
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1530-888X
1530-888X
DOI:10.1162/NECO_a_00949