Theoretical Advances in Spiking Neural Networks with Hyperdimensional Computing
Keywords:
Spiking Neural Networks, Hyperdimensional Computing, theoretical advances, computational modelsAbstract
Spiking Neural Networks (SNNs) have gained prominence in neuromorphic computing due to their biological plausibility and energy efficiency. Integrating Hyperdimensional Computing (HDC) with SNNs presents a promising avenue to enhance their computational capabilities. This paper explores theoretical advancements in leveraging HDC within SNN frameworks, focusing on encoding, computation, and learning paradigms. We review key theoretical insights, methodologies, and experimental validations, highlighting the potential of HDC to address complex cognitive tasks within the SNN architecture.
References
Kanerva, P. (2009). Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors. Cognitive Computation, 1(2), 139-159.
Gayler, R. W. (2003). What are the Brain's Uncommitted Vectors and What Might They Be Used For? Connection Science, 15(3), 245-280.
Cui, Y., Ahmad, S., Hawkins, J., & Guo, D. (2016). Continuous Online Sequence Learning with an Unsupervised Neural Network Model. Neural Computation, 28(12), 2474-2504.
Sengupta, A., Panda, P., Roy, K., & Roy, D. (2019). Spintronic Memristor through Temporal Encoding: A Comprehensive Analysis. IEEE Transactions on Nanotechnology, 18(5), 712-722.
Furber, S., Galluppi, F., Temple, S., & Plana, L. (2014). The SpiNNaker Project. Proceedings of the IEEE, 102(5), 652-665.
Published
Issue
Section
License
Copyright (c) 2021 Karim Rahemtulla (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
