Huber optimization of neural networks: a robust training method

摘要

Neural networks as an emerging modeling technique have gained much attention in the microwave area. Due to the convergence difficulty of simulators or equipment limits where parameters are sampled at extremes, the simulated or measured training data often have both gross errors and small errors. A new training method is presented in this paper which incorporates Huber concept with quasi-Newton method. The proposed method can recognize the gross errors and small errors and treat them differently. Therefore this Huber training method is much more robust than traditional least-square 12 methods, which is demonstrated through two examples, modeling of a quadratic function and Transmission Lines.