Title :
Bayesian regularized neural network for multiple gene expression pattern classification
Author :
Kelemen, Arpad ; Liang, Yulan
Author_Institution :
Dept. of Comput. & Inf. Sci., Mississippi Univ., MS, USA
Abstract :
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.
Keywords :
Markov processes; Monte Carlo methods; belief networks; genetics; learning (artificial intelligence); neural nets; parameter estimation; pattern classification; sampling methods; Bayesian regularized neural network; Gibbs sampling; generalization performance; hierarchical Bayesian setting; high level noisy feature; hybrid Monte Carlo Markov chain; hyperparameters; learning algorithms; microarray experiments; multiple complicated dynamic patterns; multiple gene expression pattern classification; network parameters; parameter estimation; regularized cost function; sequential time points; temporal patterns; uncertainties; Bayesian methods; Biomedical measurements; Clustering algorithms; Drugs; Gene expression; Neural networks; Noise level; Parameter estimation; Partitioning algorithms; Pattern classification;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223441
