Brain-Inspired Hyperdimensional Computing for Fast and Robust Neural Networks
Keywords:
hyperdimensional computing, neural networks, lightweight AIAbstract
Hyperdimensional computing (HDC) represents a model shift in neural network design which offers a lightweight and biologically inspired alternative to conventional deep learning model. Encoding the information in high dimensional binary vector in HDC which enables fast, energy-efficient, and noise-robust computations. It is specifically suitable for resource constraint environment like low-power robotics, real-time medical diagnosis, and embedded AI systems.
Downloads
References
R. T. Lakshminarasimhan, K. P. Prasad, and S. K. Nair, “Hyperdimensional computing: A new paradigm for neural networks,” IEEE Access, vol. 9, pp. 12645–12659, 2021.
Singu, Santosh Kumar. "Real-Time Data Integration: Tools, Techniques, and Best Practices." ESP Journal of Engineering & Technology Advancements 1.1 (2021): 158-172.
S. Kumari, "Agile Cloud Transformation in Enterprise Systems: Integrating AI for Continuous Improvement, Risk Management, and Scalability", Australian Journal of Machine Learning Research & Applications, vol. 2, no. 1, pp. 416-440, Mar. 2022
S. Kumari, "AI-Enhanced Agile Development for Digital Product Management: Leveraging Data-Driven Insights for Iterative Improvement and Market Adaptation", Adv. in Deep Learning Techniques, vol. 2, no. 1, pp. 49-68, Mar. 2022
Singu, Santosh Kumar. "Designing scalable data engineering pipelines using Azure and Databricks." ESP Journal of Engineering & Technology Advancements 1.2 (2021): 176-187.
S. Kumari, "AI-Driven Cybersecurity in Agile Cloud Transformation: Leveraging Machine Learning to Automate Threat Detection, Vulnerability Management, and Incident Response", J. of Art. Int. Research, vol. 2, no. 1, pp. 286-305, Apr. 2022
S. G. McKee, B. C. Sycamore, and A. Patel, “On the robustness of high-dimensional computing for adversarial attacks in AI systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 7, pp. 2713–2725, July 2022.
M. Li and J. X. Liu, “A comparison of deep learning and hyperdimensional computing for large-scale image classification,” IEEE Access, vol. 8, pp. 158619–158633, Aug. 2020.
H. L. Zhang, J. C. Liang, and G. D. Wang, “High-dimensional vector models for low-power IoT devices in embedded AI systems,” IEEE Internet of Things Journal, vol. 8, no. 12, pp. 9790–9799, Dec. 2021.
M. B. Reagen, R. G. Cypher, and R. A. Rios, “Implementing high-dimensional representations for enhanced AI models in embedded systems,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 69, no. 5, pp. 2056–2069, May 2022.
G. A. Lopez, F. Cao, and V. K. Gupta, “Fast computation with high-dimensional space: Application to robotics and AI systems,” IEEE Transactions on Automation Science and Engineering, vol. 16, no. 3, pp. 1035–1045, Aug. 2020.
J. H. Maxwell, M. R. Cook, and A. J. Bhargava, “Enhancing AI applications through high-dimensional models: A case study in medical diagnostics,” IEEE Transactions on Computational Biology and Bioinformatics, vol. 19, no. 6, pp. 2241–2249, Nov. 2022.
S. D. Jackson, S. P. Wilson, and A. P. Lin, “Neurosymbolic AI and hyperdimensional computing for real-time decision making in autonomous vehicles,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 4, pp. 1290–1303, Apr. 2022.
S. C. Chou, H. B. Koh, and C. M. Lee, “Biologically-inspired high-dimensional computing for artificial cognitive systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 12, pp. 4714–4727, Dec. 2021.
N. H. Wu and M. G. Seitz, “Evaluating high-dimensional computing models for embedded applications in low-power systems,” IEEE Embedded Systems Letters, vol. 14, no. 1, pp. 31–35, Jan. 2022.
A. Z. F. Chen and D. Y. Z. Davis, “Hyperdimensional computing in low-latency AI systems for healthcare,” IEEE Transactions on Biomedical Circuits and Systems, vol. 15, no. 6, pp. 1229–1239, Dec. 2021.
A. L. Walther, V. T. Moore, and M. L. Krishnan, “Advancements in neural network models through high-dimensional computing for autonomous systems,” IEEE Transactions on Robotics, vol. 38, no. 2, pp. 588–602, Apr. 2022.
R. V. Patel, A. B. Sanchez, and J. M. Klein, “Hyperdimensional computing for robustness and interpretability in deep learning systems,” IEEE Transactions on Artificial Intelligence, vol. 3, no. 2, pp. 438–451, Feb. 2021.
