Philip Honnold
Papers
1
Total Citations
2
H-Index
1
About
Philip Honnold is a researcher at the forefront of applied machine learning, with a focus on enhancing the efficiency and reliability of nuclear safeguards and nonproliferation efforts. His work centers on deploying machine learning models directly at the edge—on portable, low-power devices—to enable real-time, in-field analysis for inspection teams. Honnold’s major contribution lies in bridging the gap between advanced computational methods and practical field operations, demonstrating how edge AI can process sensor data locally, reduce reliance on cloud connectivity, and improve the speed and accuracy of nuclear material verification. His most-cited paper, "Machine learning at the edge to improve in-field safeguards inspections" (2024), has already garnered attention for its innovative approach to integrating lightweight neural networks into handheld instruments, a breakthrough that promises to transform how inspectors detect anomalies in remote or sensitive environments. By tackling the unique constraints of edge hardware—limited power, memory, and processing capacity—Honnold is shaping a future where AI-driven tools are not just theoretical but deployable in the field, directly supporting global security missions.
Research Focus
Key Achievements
Top Papers
- 1Machine learning at the edge to improve in-field safeguards inspections2 citations · 2024