Dylan Angus

Papers

Total Citations

H-Index

About

Dylan Angus is a researcher at the forefront of portable hardware acceleration and edge computing, with a focus on making high-performance neural network frameworks accessible on resource-constrained devices. His most-cited work, "Porting SYCL accelerated neural network frameworks to edge devices" (2023), addresses a critical challenge in modern distributed computing: enabling efficient, cross-platform AI inference at the network’s edge. By leveraging SYCL, a royalty-free, open-standard programming model, Angus demonstrates how to bridge the gap between powerful cloud-based training and real-time, low-latency deployment on edge hardware. This contribution is vital for applications ranging from smart sensors to autonomous systems, where data must be processed locally to reduce bandwidth and latency. With 3 citations to date, his work is gaining traction among researchers and engineers seeking to democratize AI acceleration. Angus’s research is particularly notable for its practical focus on portability, ensuring that neural network models can run seamlessly across diverse edge devices without vendor lock-in. His efforts are helping to shape the future of distributed intelligence, making him a rising voice in the edge computing community.