Andrew Anderson

Trinity College Dublin, Trinity College London

Papers

Total Citations

H-Index

About

Andrew Anderson is a researcher specializing in the optimization of deep neural networks (DNNs) for resource-constrained embedded and mobile systems. His work sits at the intersection of machine learning efficiency, systems optimization, and hardware-aware algorithm design, addressing one of the most pressing challenges in modern AI deployment: making powerful neural networks practical on devices with limited memory and energy budgets. Anderson's most notable contribution is TASO (Time and Space Optimization), published in 2020, which tackles the challenge of running large convolutional neural networks (CNNs) on memory-constrained hardware. This work has garnered 12 citations, reflecting its relevance to a growing community of researchers working on embedded AI applications spanning industrial robotics, automation, and mobile biometrics. His earlier 2019 poster work introduced an integer linear programming approach for ahead-of-time selection of DNN primitives, demonstrating his sustained focus on bringing mathematical rigor to neural network deployment challenges. Anderson's research is particularly valuable for students and engineers working on edge AI, where the gap between state-of-the-art model performance and real-world hardware constraints remains a critical bottleneck. His contributions offer principled, optimization-driven frameworks for bridging that gap.