Xiaolu Yang

Papers

Total Citations

H-Index

About

Xiaolu Yang is a leading researcher in computational intelligence and nonlinear dynamics, with a primary focus on developing advanced neural network architectures for solving complex time-varying systems. Yang’s most influential work introduces a varying-gain recurrent neural network that achieves super-exponential convergence rates, a breakthrough that dramatically improves the efficiency and accuracy of solving nonlinear time-varying equations. This contribution, published in 2019 and garnering 15 citations, addresses a critical bottleneck in real-time control and optimization, where traditional methods often struggle with speed and stability. By designing adaptive gain mechanisms, Yang’s network dynamically adjusts learning rates, enabling faster and more reliable convergence even under challenging system variations. This work has significant implications for robotics, signal processing, and autonomous systems, where rapid, precise solutions are essential. Yang’s research bridges theoretical rigor with practical application, offering a robust framework for tackling dynamic nonlinear problems. With a growing citation impact, Yang continues to push the boundaries of neural computation, inspiring further innovations in adaptive algorithms and real-time system control.