Towards deep learning with segregated dendrites

eLife

Timothy P Lillicrap¹  Blake A Richards²  Jordan Guerguiev³ 

[1] Department of Cell and Systems Biology, University of Toronto, Toronto, Canada;DeepMind, London, United Kingdom;Department of Biological Sciences, University of Toronto Scarborough, Toronto, Canada;

关键词: deep learning;    dendritic morphology;    neocortex;    credit assignment;    feedback alignment;    target propagation;   

DOI  :  10.7554/eLife.22901

来源: DOAJ

【 摘 要 】

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network learns to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful higher-order representations—the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the morphology of neocortical pyramidal neurons.

【 授权许可】

Unknown