Improving Performance of Retention Modeling in Ion Chromatography Using Bayesian Regularization for Neural Network Training

摘要

A better approach for training a multi-layered feed-forward network for retention modeling in ion chromatography is presented. The Bayesian regularization technique used for training the network of retention modeling in ion chromatography results in superior training performance compared to the typical Backpropagation algorithms. The presented method also has better forecasting ability.