Bayesian regularized neural network for multiple gene expression pattern classification

We developed Bayesian regularized neural network (BRNN) to characterize multiple gene expression temporal patterns from microarray experiments. One of its attractive property is that it takes into account both the high level noisy feature from microarray data and the uncertainties of the multiple models uniformly in order to avoid overfitting and to improve the generalization performance. Results are encouraging and comparison study with other popular methods is provided.