Spiking Neural Networks
3 articles · search the full text for this term
-
Neuromorphic Spiking Neural Networks and Event-Driven Hardware: Architectures, Learning Paradigms, and Experimental Realizations
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 …
Published in Current Trends in Signal Processing · Vol. 16, Issue 2, 2026 Read article
-
Development of Neuromorphic Polymer Composites Using IoT Sensing and Brain-Inspired Learning Algorithms
Abstract: This research aims to develop neuromorphic polymer composites by combining conductive sensing materials, IoT-based sensing data collection and brain-inspired learning models for adaptive response. Hybrid conductive polymer composites were developed by adding carbon nanofibers and graphene Nano platelets to a thermoplastic polymer. IoT sensors (strain, temperature) were employed to collect real-time sensing data that was combined with environmental data. A material-aware neuromorphic learning algorithm was created with event-driven spike coding …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 755–784 Read article
-
Graphene–Perovskite Hybrid Opto-Electronic Modulators for Ultra-Low Power Optical Communication
Abstract: This paper proposes a novel self-adaptive neuromorphic opto-electronic transceiver architecture designed to enhance the intelligence, adaptability, and efficiency of next-generation optical communication networks. The proposed system integrates neuromorphic computing principles with photonic signal processing to enable real-time learning, dynamic resource allocation, and autonomous compensation of channel impairments such as dispersion, nonlinearities, and noise. Unlike conventional transceivers, the developed model employs spiking neural networks embedded within opto-electronic circuits to mimic biological …
Published in Trends in Opto-electro & Optical Communication · Vol. 16, Issue 1, 2026 · pp. 41–52 Read article