Backpropagation is biologically plausible in neural networks
the verdict
REFUTED
the evidence says no
confidence 19/100
While a minority of recent theoretical models propose that cortical microcircuits might approximate error propagation, the overwhelming consensus in neuroscience and machine learning literature is that standard backpropagation is biologically implausible due to requirements like weight transport and global error signals.
Evidence for · 2
‘Backpropagation and the brain’ realized in cortical error neuron microcircuits
2025 · cited by 1
Paper [10] presents a cortical microcircuit model arguing that the brain implements a form of error backpropagation.
Evidence against · 10
Biologically plausible deep learning - but how far can we go with shallow networks?
2019 · cited by 110
Paper [0] states that error backpropagation is considered biologically implausible, prompting research into local learning rules.
See more details
More for · 1
'Backpropagation and the brain' realized in cortical error neuron microcircuits.
2026 · cited by 0
Paper [11] similarly demonstrates a biologically motivated circuit model approximating error backpropagation.
Paper [1] highlights that backpropagation's biological plausibility is challenged by weight symmetry, global error signals, and dual-phase training.
Biologically plausible local synaptic learning rules robustly implement deep supervised learning
2023 · cited by 8
Paper [2] notes that prevailing backpropagation learning rules are not necessarily biologically plausible and cannot be implemented in the brain.
Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
2024 · cited by 6
Paper [3] indicates that error backpropagation faces criticism for a lack of biological plausibility due to issues like the backward locking problem.
Self-Assembly of a Biologically Plausible Learning Circuit
2024 · cited by 6
Paper [4] confirms the neuroscience consensus that backpropagation is unlikely to be used by the brain.
Biologically plausible learning in a deep recurrent spiking network
2019 · cited by 4
Paper [5] contrasts global optimization methods like backpropagation with local synaptic mechanisms used in biological brains.
Physical Deep Learning with Biologically Plausible Training Method
2022 · cited by 3
Paper [6] notes that neural network training still relies on methods like backpropagation that are optimized for digital rather than biological processing.
Towards New Generation, Biologically Plausible Deep Neural Network Learning
2022 · cited by 3
Paper [7] describes end-to-end backpropagation as presenting a major limitation when contrasted with biological neural network processes.
Invariant visual object and face learning in the ventral cortical visual pathway: A biologically plausible model.
2026 · cited by 1
Paper [8] develops a biologically plausible model contrasting with artificial networks that do not use local synaptic learning rules.
Cellular and subcellular specialization enables biology-constrained deep learning.
2026 · cited by 1
Paper [9] points out that most modern artificial neural network algorithms are not compatible with fundamental principles of neuroscience.