Search
Abstract
A problem related to the development of a supervised learning method for recurrent spiking neural networks is addressed in the paper. The widely used Leaky-Integrate-and-Fire model has been adopted as a spike neuron model. The proposed method is based on a known SpikeProp algorithm. In detail, the developed method enables gradient descent learning of recurrent or multi-layer feedforward spiking neural networks. The research included an extended verification study for the classical XOR classification problem. In addition, the developed learning method has been used to provide a spiking neural black-box model of fast processes occurring in a pressurised water nuclear reactor. The obtained simulation results demonstrate satisfactory effectiveness of the proposed approach.
Citations
-
0
CrossRef
-
0
Web of Science
-
0
Scopus
Authors (2)
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
APPLIED SOFT COMPUTING
no. 165,
pages 112120 - 112120,
ISSN: 1568-4946 - Language:
- English
- Publication year:
- 2024
- Bibliographic description:
- Laddach K., Łangowski R.: Adjusted SpikeProp algorithm for recurrent spiking neural networks with LIF neurons// APPLIED SOFT COMPUTING -Vol. 165, (2024), s.112120-112120
- DOI:
- Digital Object Identifier (open in new tab) 10.1016/j.asoc.2024.112120
- Sources of funding:
-
- IDUB
- Verified by:
- Gdańsk University of Technology
seen 3 times
Recommended for you
Exploring Neural Networks for Musical Instrument Identification in Polyphonic Audio
- M. Blaszke,
- G. Korvel,
- B. Kostek