Pith. sign in

REVIEW 2 cited by

Dendritic cortical microcircuits approximate the backpropagation algorithm

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1810.11393 v1 pith:2XUA76YK submitted 2018-10-26 q-bio.NC cs.LGcs.NE

classification q-bio.NCcs.LGcs.NE
keywords learningdendriticmodelbackpropagationcorticalerrorsynapticactivity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience. However, the main learning mechanism behind these advances - error backpropagation - appears to be at odds with neurobiology. Here, we introduce a multilayer neuronal network model with simplified dendritic compartments in which error-driven synaptic plasticity adapts the network towards a global desired output. In contrast to previous work our model does not require separate phases and synaptic learning is driven by local dendritic prediction errors continuously in time. Such errors originate at apical dendrites and occur due to a mismatch between predictive input from lateral interneurons and activity from actual top-down feedback. Through the use of simple dendritic compartments and different cell-types our model can represent both error and normal activity within a pyramidal neuron. We demonstrate the learning capabilities of the model in regression and classification tasks, and show analytically that it approximates the error backpropagation algorithm. Moreover, our framework is consistent with recent observations of learning between brain areas and the architecture of cortical microcircuits. Overall, we introduce a novel view of learning on dendritic cortical circuits and on how the brain may solve the long-standing synaptic credit assignment problem.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Example

    cs.NE 2025-06 conditional novelty 6.0 of 10

    At matched task accuracy, e-prop trained RNNs reach neural data similarity comparable to BPTT trained RNNs on Mante 2013 and Sussillo 2015 datasets, with initialization and architecture influencing similarity more tha...

  2. The role of gain neuromodulation in layer-5 pyramidal neurons

    q-bio.NC 2025-07 conditional novelty 3.0 of 10

    A two-compartment spiking model shows that boosting coupling or apical drive raises pyramidal gain, and that the associated bursting accelerates STDP updates, yielding fast and slow weight changes.

Pith tools