ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Supervised learning using spiking neural networks

Jeyasothy, A and Dora, S and Sundaram, S and Sundararajan, N (2022) Supervised learning using spiking neural networks. [Book Chapter]

Full text not available from this repository.
Official URL: https://doi.org/10.1142/9789811247323_0010


Spiking neural networks (SNNs), termed as the third generation of neural networks, are inspired by the information processing mechanisms employed by biological neurons in the brain. Higher computational power and the energy-efficient nature of SNNs have led to the development of many learning algorithms to train SNNs for classification problems using a supervised learning paradigm. This chapter begins by providing a brief introduction to spiking neural networks along with a review of existing supervised learning algorithms for SNNs. It then highlights three recently developed learning algorithms by the authors that exploit the biological proximity of SNNs for training the SNNs. Performance evaluation of the proposed algorithms, along with a comparison with some other important existing learning algorithms for SNNs, is presented based on multiple problems from the UCI machine learning repository. The performance comparison highlights the better performance achieved by the recently developed learning algorithms. Finally, this chapter presents possible future directions of research in the area of SNNs. © 2022 World Scientific Publishing Company.

Item Type: Book Chapter
Publication: Handbook On Computer Learning And Intelligence
Publisher: World Scientific Publishing Co.
Additional Information: The copyright for this article belongs to World Scientific Publishing Co.
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 09 Jan 2023 07:02
Last Modified: 09 Jan 2023 07:02
URI: https://eprints.iisc.ac.in/id/eprint/78905

Actions (login required)

View Item View Item