David Yevick

David Yevick is a Professor at the University of Waterloo, affiliated with the Photonics and Atomic, Molecular, & Optical Physics research group. He leads the Advanced Optical Systems Lab and specializes in integrating machine learning with photonics, nonlinear optics, and quantum systems. His work spans optical communication systems, fiber nonlinearity mitigation, and quantum state analysis.

Research interests include applying neural networks and deep learning to optical device performance prediction, material science simulations, and signal processing. Recent trends in his publications focus on combining ML techniques with optical systems, such as using random forests for CNT TFET analysis and variational autoencoders for phase transition modeling.

His lab explores cutting-edge topics like self-phase modulation compensation in WDM systems and entropy-regulated data balancing. The Advanced Optical Systems Lab also develops novel photonic crystal designs and fiber compensation algorithms.