Abstract/Book

FZJ-2020-00875

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Training Delays in Spiking Neural Networks

Tetko, I. V. (Editor) ; Kůrková, V. (Editor) ; Karpov, P. (Editor) ; Theis, F. (Editor) ; State, L.FZJ* ; Vilimelis Aceituno, P. (Corresponding author)

2019

ISBN: 978-3-030-30486-7 (print), 978-3-030-30487-4 (electronic)

This record in other databases:    

Please use a persistent id in citations: doi:10.1007/978-3-030-30487-4_54

Abstract: Spiking Neural Networks (SNNs) are a promising computational paradigm, both to understand biological information processing and for low-power, embedded chips. Although SNNs are known to encode information in the precise timing of spikes, conventional artificial learning algorithms do not take this into account directly. In this work, we implement the spike timing by training the synaptic delays in a single layer SNN. We use two different approaches: a classical gradient descent and a direct algebraic method that is based on a complex-valued encoding of the spikes. Both algorithms are equally able to correctly solve simple detection tasks. Our work provides new optimization methods for the data analysis of highly time-dependent data and training methods for neuromorphic chips.

---

Contributing Institute(s):

1. Computational and Systems Neuroscience (INM-6)
2. Theoretical Neuroscience (IAS-6)
3. Jara-Institut Brain structure-function relationships (INM-10)

Research Program(s):

1. 574 - Theory, modelling and simulation (POF3-574) (POF3-574)
2. Smartstart - SMARTSTART Training Program in Computational Neuroscience (90251) (90251)

Appears in the scientific report 2020

---

Database coverage:
Nationallizenz ; SCOPUS

---