Diego Manzanas Lopez
Papers
1
Total Citations
49
H-Index
1
About
Diego Manzanas Lopez is a leading researcher in the formal verification and safety assurance of cyber-physical systems, with a particular focus on neural network-enabled autonomous systems. His most-cited work, "Parallelizable Reachability Analysis Algorithms for Feed-Forward Neural Networks" (2019, 49 citations), addresses a critical challenge: ensuring the reliability of neural networks used in safety-critical applications like self-driving cars and robotics. By developing parallelizable reachability analysis algorithms, Lopez has made it computationally feasible to formally verify the behavior of neural networks, enabling engineers to prove that these systems operate within safe bounds. This contribution is foundational for bridging the gap between deep learning's power and the rigorous safety demands of autonomous systems. Beyond this landmark paper, his research spans reachability analysis, verification of neural network control systems, and scalable formal methods. Lopez’s work has been instrumental in advancing the practical deployment of trustworthy AI in high-stakes environments, earning recognition from both the formal methods and robotics communities. For students and researchers, his research offers a compelling roadmap for making intelligent systems both capable and certifiably safe.
Research Focus
Key Achievements
Top Papers
- 1