A Neighborhood-Based Enhancement of the Gauss-Newton Bayesian Regularization Training Method
Miguel Pinzolas, Ana Toledo, Juan Luís Pedreño · Neural Computation · 2006
This work develops and tests a neighborhood-based approach to the Gauss-Newton Bayesian regularization training method for feedforward backpropagation networks. The proposed method improves the training efficiency, significantly reducing requirements on memory and computational time while maintaining the good generalization feature of the original algorithm. This version of the Gauss-Newton Bayesian regularization greatly expands the scope of application of the original method, as it allows training networks up to 100 times larger without losing performance.