Emily J. Griffis
Papers
1
Total Citations
8
H-Index
1
About
Dr. Emily J. Griffis is a leading figure at the intersection of control theory and deep learning, whose work redefines how neural networks can be used for robust, real-time system estimation. Her primary research focuses on developing theoretically-grounded, Lyapunov-based frameworks for adaptive observers, ensuring stability and reliability in complex dynamical systems. Dr. Griffis’s landmark contribution is the Lyapunov-Based Long Short-Term Memory (Lb-LSTM) Neural Network-Based Adaptive Observer, a pioneering architecture that marries the temporal memory of LSTMs with rigorous Lyapunov stability guarantees. This innovation, detailed in her highly-cited 2023 paper (8 citations), allows for accurate state estimation even in the presence of uncertainties and nonlinearities, a critical advancement for autonomous systems and industrial control. By proving that deep learning models can be both powerful and provably stable, Dr. Griffis bridges a crucial gap between empirical performance and theoretical assurance. Her work is already shaping next-generation adaptive control systems, and she is recognized as a rising star in the field, with her Lb-LSTM framework serving as a foundational reference for researchers seeking to deploy intelligent, trustworthy observers in safety-critical applications.
Research Focus
Key Achievements
Top Papers
- 1