Energy efficient synaptic plasticity

Abstract
Data availability
Article and author information
Metrics

Abstract

Many aspects of the brain's design can be understood as the result of evolutionary drive towards metabolic efficiency. In addition to the energetic costs of neural computation and transmission, experimental evidence indicates that synaptic plasticity is metabolically demanding as well. As synaptic plasticity is crucial for learning, we examine how these metabolic costs enter in learning. We find that when synaptic plasticity rules are naively implemented, training neural networks requires extremely large amounts of energy when storing many patterns. We propose that this is avoided by precisely balancing labile forms of synaptic plasticity with more stable forms. This algorithm, termed synaptic caching, boosts energy efficiency manifold and can be used with any plasticity rule, including back-propagation. Our results yield a novel interpretation of the multiple forms of neural synaptic plasticity observed experimentally, including synaptic tagging and capture phenomena. Furthermore our results are relevant for energy efficient neuromorphic designs.

Data availability

Simulation scripts can be found at https://github.com/vanrossumlab/li_vanrossum_19.

The following previously published data sets were used

(1999) Data from: The MNIST database of handwritten digits
The MNIST database of handwritten digits.

http://yann.lecun.com/exdb/mnist/

Article and author information

Author details

Ho Ling Li

School of Psychology, University of Nottingham, Nottingham, United Kingdom

Competing interests
No competing interests declared.

"This ORCID iD identifies the author of this article:" 0000-0002-5654-0183
Mark CW van Rossum

School of Psychology and School of Mathematical Sciences, University of Nottingham, Nottingham, United Kingdom

For correspondence
mark.vanrossum@nottingham.ac.uk

Competing interests
Mark CW van Rossum, Reviewing editor, eLife.

"This ORCID iD identifies the author of this article:" 0000-0001-6525-6814

Funding

Leverhulme Trust (RPG-2017-404)

Mark CW van Rossum

Engineering and Physical Sciences Research Council (EP/R030952/1)

Mark CW van Rossum

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Copyright

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.