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
-
Eight challenges in developing theory of intelligence.Front Comput Neurosci. 2024 Jul 24;18:1388166. doi: 10.3389/fncom.2024.1388166. eCollection 2024. Front Comput Neurosci. 2024. PMID: 39114083 Free PMC article.
-
A hierarchical reinforcement learning model explains individual differences in attentional set shifting.Cogn Affect Behav Neurosci. 2024 Dec;24(6):1008-1022. doi: 10.3758/s13415-024-01223-7. Epub 2024 Sep 23. Cogn Affect Behav Neurosci. 2024. PMID: 39313748 Free PMC article.
-
An Agent-Based Model to Reproduce the Boolean Logic Behaviour of Neuronal Self-Organised Communities through Pulse Delay Modulation and Generation of Logic Gates.Biomimetics (Basel). 2024 Feb 9;9(2):101. doi: 10.3390/biomimetics9020101. Biomimetics (Basel). 2024. PMID: 38392147 Free PMC article.
-
Neurorobotic reinforcement learning for domains with parametrical uncertainty.Front Neurorobot. 2023 Oct 25;17:1239581. doi: 10.3389/fnbot.2023.1239581. eCollection 2023. Front Neurorobot. 2023. PMID: 37965072 Free PMC article.
-
Ten quick tips for deep learning in biology.PLoS Comput Biol. 2022 Mar 24;18(3):e1009803. doi: 10.1371/journal.pcbi.1009803. eCollection 2022 Mar. PLoS Comput Biol. 2022. PMID: 35324884 Free PMC article. No abstract available.
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