Backpropagation and the brain
- PMID: 32303713
- DOI: 10.1038/s41583-020-0277-3
Backpropagation and the brain
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.
Similar articles
-
An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity.Neural Comput. 2017 May;29(5):1229-1262. doi: 10.1162/NECO_a_00949. Epub 2017 Mar 23. Neural Comput. 2017. PMID: 28333583 Free PMC article.
-
A more biologically plausible learning rule than backpropagation applied to a network model of cortical area 7a.Cereb Cortex. 1991 Jul-Aug;1(4):293-307. doi: 10.1093/cercor/1.4.293. Cereb Cortex. 1991. PMID: 1822737
-
Meta-learning biologically plausible plasticity rules with random feedback pathways.Nat Commun. 2023 Mar 31;14(1):1805. doi: 10.1038/s41467-023-37562-1. Nat Commun. 2023. PMID: 37002222 Free PMC article.
-
Control of synaptic plasticity in deep cortical networks.Nat Rev Neurosci. 2018 Feb 16;19(3):166-180. doi: 10.1038/nrn.2018.6. Nat Rev Neurosci. 2018. PMID: 29449713 Review.
-
Backpropagation through time and the brain.Curr Opin Neurobiol. 2019 Apr;55:82-89. doi: 10.1016/j.conb.2019.01.011. Epub 2019 Mar 7. Curr Opin Neurobiol. 2019. PMID: 30851654 Review.
Cited by
-
Spine dynamics in the brain, mental disorders and artificial neural networks.Nat Rev Neurosci. 2021 Jul;22(7):407-422. doi: 10.1038/s41583-021-00467-3. Epub 2021 May 28. Nat Rev Neurosci. 2021. PMID: 34050339 Review.
-
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias.Front Neurosci. 2021 Feb 18;15:633674. doi: 10.3389/fnins.2021.633674. eCollection 2021. Front Neurosci. 2021. PMID: 33679315 Free PMC article.
-
How far is brain-inspired artificial intelligence away from brain?Front Neurosci. 2022 Dec 9;16:1096737. doi: 10.3389/fnins.2022.1096737. eCollection 2022. Front Neurosci. 2022. PMID: 36570836 Free PMC article. Review.
-
Backpropagation With Sparsity Regularization for Spiking Neural Network Learning.Front Neurosci. 2022 Apr 14;16:760298. doi: 10.3389/fnins.2022.760298. eCollection 2022. Front Neurosci. 2022. PMID: 35495028 Free PMC article.
-
A maturational frequency discrimination deficit may explain developmental language disorder.Psychol Rev. 2024 Apr;131(3):695-715. doi: 10.1037/rev0000436. Epub 2023 Jul 27. Psychol Rev. 2024. PMID: 37498700 Free PMC article.
References
-
- Hebb, D. O. The Organization of Behavior: A Neuropsychological Approach (John Wiley & Sons, 1949).
-
- Markram, H. & Sakmann, B. Action potentials propagating back into dendrites trigger changes in efficacy of single-axon synapses between layer V pyramidal neurons. Soc. Neurosci. Abstr. 21, 2007 (1995).
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Miscellaneous