Finite-Time Stable Versions of the Continuous Newton Method and Applications to Neural Networks

AbstractControl theory has become a focus of research for evaluation and synthesis of numerical algorithms. In this paper, a finite-time version of the continuous Newton method is proposed using finite-time stability theory. Moreover, robustness of the proposed method under computational errors is discussed. A finite-time continuous quasi Gauss-Newton method is also derived. The effectiveness of the proposed methods in neural network problems is illustrated via simulations.