Justin Whitehouse

Columbia University, Coventry (United Kingdom)

Papers

Total Citations

H-Index

About

Justin Whitehouse’s research bridges the critical gap between deep learning and rigorous engineering principles, with a focus on ensuring the safety and reliability of AI systems deployed in high-stakes domains such as autonomous driving, robotics, and cybersecurity. His most cited work, “Bringing Engineering Rigor to Deep Learning” (2019, 4 citations), addresses the pressing need for predictable, verifiable behavior in deep neural networks, particularly on corner-case inputs where failures can have catastrophic consequences. Whitehouse advocates for formal validation methods and systematic testing frameworks, drawing from traditional software engineering to make deep learning more trustworthy. Earlier in his career, he explored novel sensing techniques, as seen in “New Principle of Rangefinding Using Blurred Images” (1989, 3 citations), which established a method for extracting range data by analyzing blur profiles in the focal plane—a creative approach with implications for computer vision and robotics. While his citation counts are modest, Whitehouse’s work is notable for its forward-looking emphasis on engineering rigor in AI, a topic of growing importance as deep learning systems become ubiquitous. His contributions inspire researchers to prioritize correctness and safety alongside performance.