KIP publications

 
year 2018
author(s) Luziwei Leng*, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici*
title Spiking neurons with short-term synaptic plasticity form superior generative networks
KIP-Nummer HD-KIP 18-72
KIP-Gruppe(n) F9
document type Paper
source Scientific Reports 8, 10651 (2018)
doi 10.1038/s41598-018-28999-2
Abstract (en)

Spiking networks that perform probabilistic inference have been proposed both as models of cortical computation and as candidates for solving problems in machine learning. However, the evidence for spike-based computation being in any way superior to non-spiking alternatives remains scarce. We propose that short-term synaptic plasticity can provide spiking networks with distinct computational advantages compared to their classical counterparts. When learning from high-dimensional, diverse datasets, deep attractors in the energy landscape often cause mixing problems to the sampling process. Classical algorithms solve this problem by employing various tempering techniques, which are both computationally demanding and require global state updates. We demonstrate how similar results can be achieved in spiking networks endowed with local short-term synaptic plasticity. Additionally, we discuss how these networks can even outperform tempering-based approaches when the training data is imbalanced. We thereby uncover a powerful computational property of the biologically inspired, local, spike-triggered synaptic dynamics based simply on a limited pool of synaptic resources, which enables them to deal with complex sensory data.

bibtex
@article{leng2018spiking,
  author   = {Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici},
  title    = {Spiking neurons with short-term synaptic plasticity form superior generative networks},
  journal  = {Scientific Reports},
  year     = {2018},
  volume   = {8},
  number   = {10651},
  pages    = {},
  month    = {July},
  doi      = {10.1038/s41598-018-28999-2},
  url      = {https://www.nature.com/articles/s41598-018-28999-2}
}
Sample Image
URL arXiv link
URL Scientific Reports
up
KIP - Bibliothek
Im Neuenheimer Feld 227
Raum 3.402
69120 Heidelberg