Neuromorphic Spiking Neural Networks and Event-Driven Hardware: Architectures, Learning Paradigms, and Experimental Realizations

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 16 | 02 | Page :
By

Diksha Rajput,

Lakshya Vijayvargiya,

Anuradha,

  1. Student, Department of Computer Science & Engineering, Jaipur Engineering College and Research Centre, Jaipur, Rajasthan, India
  2. Student, Department of Computer Science & Engineering, Jaipur Engineering College and Research Centre, Jaipur, Rajasthan, India
  3. Assistant Professor, Department of Computer Science & Engineering, Jaipur Engineering College and Research Centre, Jaipur, Rajasthan, India

Abstract

With the current computational boom the research community is seeking for more sustainable energy efficient i.e. biologically inspired models of conventional Artificial Neural Networks (ANNs). Spiking Neural Networks (SNNs) known as the third generation of neural network models, provide a revolutionary approach by mimicking the asynchronized event-driven and temporally accurate signaling of the mammalian brain. Whereas conventional deep learning models operate with real-valued activations and dense matrix multiplications, SNNs use binary spikes to encode and transmit information. This allows Spiking Neural Networks (SNNs) to be event driven and to be implemented with low-power neuromorphic hardware. This comprehensive research paper analyzes major neural models, learning techniques like spike timing dependent plasticity a surrogate gradients, and modern neuromorphic hardware used for event driven computing. Comparative experimental data show event-driven neuromorphic systems can achieve up to 1000× better energy efficiency during the inference than standard GPU platforms. This analysis address key implementation bottlenecks, including back propagation limitations, software tooling gaps and conversion accuracy losses. Ultimately, this analysis shows that combining SNNs with the neuromorphic hardware have strong potential for future low power and real-time edge intelligent systems across the different fields enabling computing architectures for next-generation applications globally that are scalable, adaptable, intelligent, sustainable, autonomous, and energy-aware.

Keywords: Spiking Neural Networks, Neuromorphic Engineering, Event-Driven Computing, Low-power AI, and robotics.

How to cite this article: Diksha Rajput, Lakshya Vijayvargiya, Anuradha. Neuromorphic Spiking Neural Networks and Event-Driven Hardware: Architectures, Learning Paradigms, and Experimental Realizations. Current Trends in Signal Processing. 2026; 16(02):-.
How to cite this URL: Diksha Rajput, Lakshya Vijayvargiya, Anuradha. Neuromorphic Spiking Neural Networks and Event-Driven Hardware: Architectures, Learning Paradigms, and Experimental Realizations. Current Trends in Signal Processing. 2026; 16(02):-. Available from: https://journals.stmjournals.com/ctsp/article=2026/view=251800

References

  1. Davies M, Srinivasa N, Lin TH, Chinya G, Cao Y, Choday SH, Dimou G, Joshi P, Imam N, Jain S, Liao Y. Loihi: A neuromorphic manycore processor with on-chip learning. Ieee micro. 2018 Jan 16;38(1):82-99.
  2. Merolla PA, Arthur JV, Alvarez-Icaza R, Cassidy AS, Sawada J, Akopyan F, Jackson BL, Imam N, Guo C, Nakamura Y, Brezzo B. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science. 2014 Aug 8;345(6197):668-73.
  3. Fang W, Chen Y, Ding J, Yu Z, Masquelier T, Chen D, Huang L, Zhou H, Li G, Tian Y. Spikingjelly: An open- source machine learning infrastructure platform for spike- based intelligence. Science Advances. 2023 Oct 6;9(40):eadi1480.
  4. Math S, Madhuri HD, Yadhav V, Patil M, Selvakumar P. Quantum-Inspired or Neuromorphic Discrete-Event Computing Paradigms for Future Ubiquitous Systems. InUbiquitous Computing for Discrete Event Systems 2026 (pp. 99-138). IGI Global Scientific Publishing.
  5. Modha DS, Akopyan F, Andreopoulos A, Appuswamy R, Arthur JV, Cassidy AS, Datta P, DeBole MV, Esser SK, Otero CO, Sawada J. Neural inference at the frontier of energy, space, and time. Science. 2023 Oct 20;382(6668):329-35.
  6. Zenke F, Vogels TP. The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks. Neural computation. 2021 Mar 26;33(4):899-925.
  7. Shrestha SB, Orchard G. Slayer: Spike layer error reassignment in time. Advances in neural information processing systems. 2018;31.
  8. Indiveri G, Liu SC. Memory and information processing in neuromorphic systems. Proceedings of the IEEE. 2015 Jul 15;103(8):1379-97.
  9. Cheng Y, Wang M, Hao Z, Buyya R. Brain-inspired AI for Edge Intelligence: a systematic review. arXiv preprint arXiv:2603.26722. 2026 Mar 19.
  10. Cheng Y, Wang M, Hao Z, Buyya R. Brain-inspired AI for Edge Intelligence: a systematic review. arXiv preprint arXiv:2603.26722. 2026 Mar 19.
Ahead of Print Subscription Review Article
Volume 16
02
Received 22/07/2026
Accepted 05/08/2026
Published 05/08/2026
Publication Time 14 Days

Login

My IP

PlumX Metrics