Dendritic error backpropagation in deep cortical microcircuits

Abstract

Animal behaviour depends on learning to associate sensory stimuli with the desired motor command. Understanding how the brain orchestrates the necessary synaptic modifications across different brain areas has remained a longstanding puzzle. Here, we introduce a multi-area neuronal network model in which synaptic plasticity continuously adapts the network towards a global desired output. In this model synaptic learning is driven by a local dendritic prediction error that arises from a failure to predict the top-down input given the bottom-up activities. Such errors occur at apical dendrites of pyramidal neurons where both long-range excitatory feedback and local inhibitory predictions are integrated. When local inhibition fails to match excitatory feedback an error occurs which triggers plasticity at bottom-up synapses at basal dendrites of the same pyramidal neurons. We demonstrate the learning capabilities of the model in a number of tasks and show that it approximates the classical error backpropagation algorithm. Finally, complementing this cortical circuit with a disinhibitory mechanism enables attention-like stimulus denoising and generation. Our framework makes several experimental predictions on the function of dendritic integration and cortical microcircuits, is consistent with recent observations of cross-area learning, and suggests a biological implementation of deep learning.

27 pages, 5 figures, 10 pages supplementary information

References in corpus (2)

• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• Cortical microcircuits as gated-recurrent neural networks

Cited by in corpus (8)

• Artificial neural networks for neuroscientists: A primer
• Adaptive Extreme Edge Computing for Wearable Devices
• Unsupervised Learning by Competing Hidden Units
• Biologically plausible deep learning -- but how far can we go with shallow networks?
• Feedback alignment in deep convolutional networks
• Sampling-based probabilistic inference emerges from learning in neural circuits with a cost on reliability
• Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks
• The Roles of Supervised Machine Learning in Systems Neuroscience