Patrick Lincoln
Papers
1
Total Citations
6
H-Index
1
About
Patrick Lincoln is a leading figure in formal methods, cyber-physical systems, and trustworthy machine learning. His pioneering work bridges the gap between rigorous verification and the unpredictable nature of real-world AI. Lincoln’s major contributions include foundational advances in automated theorem proving and the development of techniques to ensure reliability in safety-critical systems, from autonomous vehicles to surgical robotics. His highly cited research, such as the 2018 paper "Model, Data and Reward Repair: Trusted Machine Learning for Markov Decision Processes" (6 citations), introduces a paradigm for guaranteeing safety and liveness in ML models deployed in high-stakes environments. By focusing on model, data, and reward repair, Lincoln has shaped how researchers approach the verification of learning-enabled systems. His work is instrumental in establishing a formal foundation for trusted AI, ensuring that as machine learning becomes more pervasive, it does so with provable assurances. Lincoln’s influence extends across computer science, where his contributions continue to inspire new generations of researchers dedicated to building reliable, verifiable autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1