9
Abstract. This comprehensive review explores the rapidly advancing
field of Spiking Neural Networks (SNNs), particularly emphasizing their
computational capabilities and potential for energy-efficient computing.
SNNs distinguish themselves from traditional neural networks by skill-
fully processing complex, time-sensitive binary inputs through intricate
encoding strategies and dynamic learning algorithms. This paper dis-
cusses various encoding techniques and evaluates several neuron mod-
els integral to SNN architecture, such as the Leaky Integrate-and-Fire,
Hodgkin-Huxley, and Izhikevich models. These models are appraised for
their trade-offs between computational simplicity and biological plausi-
bility. Additionally, we examine the energy-saving expertise of SNNs rel-
ative to their traditional counterparts, identifying challenges in scaling
and the intricacy of training. The review explores a spectrum of training
techniques for SNNs, including supervised, unsupervised, and reinforce-
ment learning approaches. This paper culminates by highlighting imper-
ative future research directions in SNNs. It underscores the pressing need
for developing sophisticated training algorithms and customizing mod-
els to augment efficiency and versatility in energy-conscious computing.
These focal points are suggested as pivotal for driving the field forward
and unlocking the full potential of SNNs in real-world applications.
https://doi.org/10.1007/978-3-031-62799-6_2
Cite this paper
Ayasi, B., García-Vico, Á.M., Carmona, C.J., Saleh, M. (2024). Advancing Computational Frontiers: Spiking Neural Networks in High-Energy Efficiency Computing Across Diverse Domains. In: Alonso-Betanzos, A., et al. Advances in Artificial Intelligence. CAEPIA 2024. Lecture Notes in Computer Science(), vol 14640. Springer, Cham. https://doi.org/10.1007/978-3-031-62799-6_2