Classification with Bayesian Neural Networks
I submitted entries for the two classification problems — “Catalysis” and “Gatineau” — in the Evaluating Predictive Uncertainty Challenge. My entry for Catalysis was the best one; my entry for Gatineau was the third best, behind two similar entries by Nitesh Chawla.
The Catalysis dataset was later revealed to be about predicting a property of yeast proteins from expression levels of the genes encoding them. The nature of the Gatineau dataset has not been revealed, for proprietary reasons. The two datasets are similar in number of input variables that are available for predicting the binary outcome (617 for Catalysis, 1092 for Gatineau). They differ substantially in the number of cases available for training (1173 for Catalysis, 5176 for Gatineau) and in the fractions of cases that are in the two classes (43%/57% for Catalysis, 9%/91% for Gatineau).
KeywordsNeural Network Model Hide Unit Markov Chain Monte Carlo Method Training Case Bayesian Neural Network
Unable to display preview. Download preview PDF.
- Neal, R.M.: Probabilistic Inference Using Markov Chain Monte Carlo Methods, Technical Report CRG-TR-93-1, Department of Computer Science, University of Toronto, 144 p. (1993) Available from, http://www.cs.utoronto.ca/~radford/
- Neal, R.M., Zhang, J.: High Dimensional Classification with Bayesian Neural Networks and Dirichlet Diffusion Trees. In: Guyon, I., Gunn, S., Nikravesh, M., Zadeh, L. (eds.) Feature Extraction, Foundations and Applications. Studies in Fuzziness and Soft Computing. Physica-Verlag, Springer, Heidelberg (2006)Google Scholar