Natural-gradient learning for spiking neurons.

Kreutzer, Elena; Senn, Walter; Petrovici, Mihai A (2022). Natural-gradient learning for spiking neurons. eLife, 11 eLife Sciences Publications 10.7554/eLife.66526

Preview

Text elife-66526-v1.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (4MB) | Preview

In many normative theories of synaptic plasticity, weight updates implicitly depend on the chosen parametrization of the weights. This problem relates, for example, to neuronal morphology: synapses which are functionally equivalent in terms of their impact on somatic firing can differ substantially in spine size due to their different positions along the dendritic tree. Classical theories based on Euclidean-gradient descent can easily lead to inconsistencies due to such parametrization dependence. The issues are solved in the framework of Riemannian geometry, in which we propose that plasticity instead follows natural-gradient descent. Under this hypothesis, we derive a synaptic learning rule for spiking neurons that couples functional efficiency with the explanation of several well-documented biological phenomena such as dendritic democracy, multiplicative scaling, and heterosynaptic plasticity. We therefore suggest that in its search for functional synaptic plasticity, evolution might have come up with its own version of natural-gradient descent.

Interest & Impact

Downloads

22 since deposited on 26 Apr 2022
22 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item