Cellular and subcellular specialization enables biology-constrained deep learning.

Learning depends on changes in neuronal synaptic strengths. While cellular mechanisms of plasticity have been extensively studied experimentally, our understanding of how plasticity is organized across neural populations comes largely from training artificial neural networks (ANNs). However, most modern ANN architectures and algorithms are not compatible with fundamental principles of neuroscience. Here we leverage recent experimental evidence to test an emergent theory that biological learning depends on neuronal cell type specialization and compartmentalized signaling within neuronal dendrites. We demonstrate that multilayer ANNs comprised of separate excitatory and inhibitory cell types, and neuronal units with separate dendrite compartments, can be trained to accurately classify images using a fully biology-compatible deep learning algorithm called dendritic target propagation. By adhering to strict biological constraints, this model provides insight into biological mechanisms of learning and makes experimentally testable predictions regarding the roles of specific cell types in coordinating learning across multiple circuit layers.