Neuromorphic Computing for Spiking Neural Network Applications

Neelesh, Mungoli and Aditya, Singh (2025) Neuromorphic Computing for Spiking Neural Network Applications. International Journal of Informatics and Data Science Research, 2 (3). pp. 37-54. ISSN 2997-3961 (In Press)

Text Neuromorphic Computing.pdf Download (751kB)

Abstract

Neuromorphic computing emulates the fundamental principles of biological neural systems by tightly integrating memory and processing to replicate the highly parallel, event-driven nature of the human brain. A key advantage of this architecture is its ultra-low power consumption, which arises from event-based signaling: individual neurons only communicate when they detect relevant input spikes, drastically reducing idle-state energy usage. Meanwhile, Spiking Neural Networks (SNNs) align well with this paradigm, leveraging temporal coding via discrete spike events rather than continuous activation values. This discrete, asynchronous behavior enables real-time processing and efficient adaptation to streaming sensory data, making SNNs particularly compelling for tasks like event-based vision, time-series analysis, or control in edge computing scenarios.

Item Type:	Article
Subjects:	Q Science > Q Science (General)
Divisions:	Postgraduate > Master's of Islamic Education
Depositing User:	Journal Editor
Date Deposited:	19 Mar 2025 09:18
Last Modified:	19 Mar 2025 09:18
URI:	http://eprints.umsida.ac.id/id/eprint/15850

Actions (login required)

View Item