Format

Send to

Choose Destination
Elife. 2017 Dec 5;6. pii: e22901. doi: 10.7554/eLife.22901.

Towards deep learning with segregated dendrites.

Author information

1
Department of Biological Sciences, University of Toronto Scarborough, Toronto, Canada.
2
Department of Cell and Systems Biology, University of Toronto, Toronto, Canada.
3
DeepMind, London, United Kingdom.
4
Learning in Machines and Brains Program, Canadian Institute for Advanced Research, Toronto, Canada.

Abstract

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.

KEYWORDS:

computational biology; credit assignment; deep learning; dendritic morphology; feedback alignment; neocortex; neuroscience; none; systems biology; target propagation

PMID:
29205151
PMCID:
PMC5716677
DOI:
10.7554/eLife.22901
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for eLife Sciences Publications, Ltd Icon for PubMed Central
Loading ...
Support Center