Dendritic cortical microcircuits approximate the backpropagation algorithm

TL;DR

This paper presents a biologically plausible neural network model that uses dendritic compartments to approximate backpropagation, bridging neuroscience and deep learning for error-driven learning.

Contribution

The authors introduce a dendritic neuron model that performs error backpropagation-like learning without separate phases, aligning with cortical microcircuit architecture.

Findings

Model successfully performs regression and classification tasks.

Analytically shown to approximate backpropagation.

Consistent with cortical microcircuit observations.

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.