Title :
Neural networks for predicting Kaposi´s sarcoma
Author :
Husmeier, Dirk ; Patton, Gillian S. ; McClure, Myra O. ; Harris, John R W ; Roberts, Stephen J.
Author_Institution :
Imperial Coll. of Sci., Technol. & Med., London, UK
Abstract :
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
Keywords :
Bayes methods; Markov processes; Monte Carlo methods; medical diagnostic computing; neural nets; probability; Bayesian neural networks; Kaposi sarcoma prediction; Markov chain; Monte Carlo method; backpropagation; data sets; medical diagnostic computing; probability; Acquired immune deficiency syndrome; Bayesian methods; Biomedical equipment; Educational institutions; Input variables; Medical services; Monte Carlo methods; Neural networks; Switches; Tumors;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.836274
