Co Design
Co-design is a synergistic approach that simultaneously optimizes both the algorithm and hardware components of a system, aiming to achieve superior performance and efficiency compared to independent optimization. Current research focuses on diverse applications, including AI accelerators, robotic control, and large language model deployment, employing techniques like reinforcement learning, Bayesian optimization, and neural architecture search to achieve this co-optimization. This interdisciplinary field is significantly impacting various domains by enabling the development of more efficient, robust, and cost-effective systems across diverse applications, from edge computing to medical AI.
Papers
Recent Advances in Scalable Energy-Efficient and Trustworthy Spiking Neural networks: from Algorithms to Technology
Souvik Kundu, Rui-Jie Zhu, Akhilesh Jaiswal, Peter A. Beerel
On-sensor Printed Machine Learning Classification via Bespoke ADC and Decision Tree Co-Design
Giorgos Armeniakos, Paula L. Duarte, Priyanjana Pal, Georgios Zervakis, Mehdi B. Tahoori, Dimitrios Soudris