Corey Lammie
Papers
2
Total Citations
101
H-Index
2
About
Corey Lammie is a researcher specializing in edge computing, hardware acceleration, and deep learning inference, with a particular focus on deploying neural networks in resource-constrained environments. His most notable contribution, "Low-Power and High-Speed Deep FPGA Inference Engines for Weed Classification at the Edge" (2019), has garnered 98 citations and demonstrates his ability to bridge the gap between cutting-edge machine learning and practical hardware implementation. In this work, Lammie developed GPU- and FPGA-accelerated binarized deep neural networks tailored for real-world agricultural applications, specifically robotic weed species classification — a domain where power efficiency and processing speed are critical constraints. By leveraging deterministic binarization techniques, his approach achieves competitive inference performance while significantly reducing the computational overhead typically associated with GPU-based systems. A live demonstration of this work at a subsequent conference further underscores his commitment to translating research into tangible, deployable solutions. Lammie's contributions sit at an exciting intersection of precision agriculture, neuromorphic engineering, and embedded AI, making his work highly relevant to researchers and engineers seeking efficient deep learning solutions for autonomous and edge-based systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2