KIP publications

year 2020
author(s) Elena Kreutzer, Walter Senn*, Mihai A. Petrovici*
title Natural gradient learning for spiking neurons
KIP-Nummer HD-KIP 20-97
KIP-Gruppe(n) F9
document type Paper
source arXiv:2011.11710
Abstract (en)

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

bibtex
@article{kreutzer2020natural,
  author   = {Elena Kreutzer, Walter Senn*, Mihai A. Petrovici*},
  title    = {Natural gradient learning for spiking neurons},
  journal  = {arXiv},
  year     = {2020},
  volume   = {},
  pages    = {},
  url      = {https://arxiv.org/abs/2011.11710}
}
Sample Image
Datei pdf
URL arXiv link
KIP - Bibliothek
Im Neuenheimer Feld 227
Raum 3.402
69120 Heidelberg