Mi Zhou

Deep transfer learning for system identification using long short-term memory neural networks

2022 · arXiv (Cornell University)

Recurrent neural networks (RNNs) have many advantages over more traditional system identification techniques. They may be applied to linear and nonlinear systems, and they require fewer modeling assumptions. However, these neural network models may also …

Simulation Research on Inception of Upward Leader of Lightning Receptor in Wind Turbine

2023

Lightning poses a huge threat to wind turbine operation, and it is essential to clarify the factors that affect the lightning protection capability of the lightning receptor at the blade tips of wind turbines. A …

Ultra-efficient physical field computing by complex-valued network quantization

2026 · Nature Communications

Neural network quantization is an established technique for compressing real-valued models, but its application to complex-valued networks-essential in electromagnetics, acoustics, and quantum physics-remains underdeveloped. Conventional quantization methods treat real and imaginary components as independent channels, …