论文信息 - Neural networks for predicting Kaposi's sarcoma

Neural networks for predicting Kaposi's sarcoma

This paper demonstrates a medical application of Bayesian neural networks, whose parameters and hyper-parameters are sampled from the posterior distribution by means of Monte Carlo Markov chain. The main objective is the determination of the relevance of various input variables. The paper focuses on typical difficulties one has to face when dealing with sparse data sets.

Stephen J. Roberts | Dirk Husmeier | Gillian S. Patton | Myra O. McClure | John R. W. Harris

[1] Mahesan Niranjan,et al. Parcel: Feature Subset Selection in Variable Cost Domains , 1998 .

[2] R. A. Fox,et al. Introduction to Mathematical Statistics , 1947 .

[3] David J. C. MacKay,et al. Bayesian Interpolation , 1992, Neural Computation.

[4] Geoffrey E. Hinton,et al. Bayesian Learning for Neural Networks , 1995 .

[5] Paul G. Hoel,et al. Introduction to Mathematical Statistics. , 1964 .

[6] William D. Penny,et al. An empirical evaluation of Bayesian sampling with hybrid Monte Carlo for training neural network classifiers , 1999, Neural Networks.