In-training and post-training generalization methods: The case of ppar — α and ppar — γ agonists
B. Keshavarz-Hedayati, P. Guangyuan, Ali Jooya, N.J. Dimopoulos · 2015
In this paper, the effects of regularization on the generalization capabilities of a neural network model are analyzed. We compare the performance of Levenberg-Marquardt and Bayesian Regularization algorithms with and without post-training regularization. We show that although Bayesian Regularization performs slightly better than Levenberg-Marquardt, the model trained using Levenberg-Marquardt holds more information about the data set which by proper post-processing regularization can be extracted. This post-processing regularization imposes smoothness and similarity.