Backpropagation and the brain
Top Cited Papers
- 17 April 2020
- journal article
- review article
- Published by Springer Science and Business Media LLC in Nature Reviews Neuroscience
- Vol. 21 (6), 335-346
- https://doi.org/10.1038/s41583-020-0277-3
Abstract
During learning, the brain modifies synapses to improve behaviour. In the cortex, synapses are embedded within multilayered networks, making it difficult to determine the effect of an individual synaptic modification on the behaviour of the system. The backpropagation algorithm solves this problem in deep artificial neural networks, but historically it has been viewed as biologically problematic. Nonetheless, recent developments in neuroscience and the successes of artificial neural networks have reinvigorated interest in whether backpropagation offers insights for understanding learning in the cortex. The backpropagation algorithm learns quickly by computing synaptic updates using feedback connections to deliver error signals. Although feedback connections are ubiquitous in the cortex, it is difficult to see how they could deliver the error signals required by strict formulations of backpropagation. Here we build on past and recent developments to argue that feedback connections may instead induce neural activities whose differences can be used to locally approximate these signals and hence drive effective learning in deep networks in the brain.Keywords
This publication has 120 references indexed in Scilit:
- Preference Distributions of Primary Motor Cortex Neurons Reflect Control Solutions Optimized for Limb BiomechanicsNeuron, 2013
- Vivid visual mental imagery in the absence of the primary visual cortexZeitschrift für Neurologie, 2011
- Properties of the thalamic projection from the posterior medial nucleus to primary and secondary somatosensory cortices in the mouseProceedings of the National Academy of Sciences of the United States of America, 2011
- Metamers of the ventral streamNature Neuroscience, 2011
- Dimensions of a Projection Column and Architecture of VPM and POm Axons in Rat Vibrissal CortexCerebral Cortex, 2010
- Hierarchical Bayesian inference in the visual cortexJournal of the Optical Society of America A, 2003
- A Neural Substrate of Prediction and RewardScience, 1997
- Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPsScience, 1997
- A neuronal learning rule for sub-millisecond temporal codingNature, 1996
- Simple memory: a theory for archicortexPhilosophical Transactions of the Royal Society of London. B, Biological Sciences, 1971