Learning population of spiking neural networks with perturbation of conductances

Piotr Suszyński , Paweł Wawrzyński


In this paper a method is presented for learning of spiking neural networks. It is based on perturbation of synaptic conductances. While this approach is known to be model-free, it is also known to be slow, because it applies improvement direction estimates with large variance. Two ideas are analysed to alleviate this problem: First, learning of many networks at the same time instead of one. Second, autocorrelation of perturbations in time. In the experimental study the method is validated on three learning tasks in which information is conveyed with frequency and spike timing. Index terms-Spiking neural networks, learning.
Author Piotr Suszyński - [Warsaw University of Technology (PW)]
Piotr Suszyński,,
- Politechnika Warszawska
, Paweł Wawrzyński (FEIT / AK)
Paweł Wawrzyński,,
- The Institute of Control and Computation Engineering
Publication size in sheets0.5
Book Alippi C, Bu L, Zhao D (eds.): Proceedings of the International Joint Conference on Neural Networks 2013 Dallas, 2013, NY, USA, IEEE, ISBN 978-1-4673-6129-3, 2628 p.
URL http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6706756&tag=1
Languageen angielski
WawPa1301_MSNN.pdf 161.82 KB
Score (nominal)15
Score sourceconferenceIndex
ScoreMinisterial score = 10.0, 09-01-2020, BookChapterMatConfByIndicator
Ministerial score (2013-2016) = 15.0, 09-01-2020, BookChapterMatConfByIndicator
Publication indicators Scopus Citations = 0; WoS Citations = 0
Citation count*
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Are you sure?