Bayesian classification with Gaussian processes
Christopher K. I. Williams, David Barber · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1998
We consider the problem of assigning an input vector to one of m classes by predicting P(c|x) for c=1,...,m. For a two-class problem, the probability of class one given x is estimated by /spl sigma/(y(x)), where /spl sigma/(y)=1/(1+e/sup -y/). A Gaussian process prior is placed on y(x), and is combined with the training data to obtain predictions for new x points. We provide a Bayesian treatment, integrating over uncertainty in y and in the parameters that control the Gaussian process prior the necessary integration over y is carried out using Laplace's approximation. The method is generalized to multiclass problems (m>2) using the softmax function. We demonstrate the effectiveness of the method on a number of datasets.
Cited by 766 works. doi:10.1109/34.735807 Open-access PDF
Authors
References
- The Nature of Statistical Learning Theory
- Generalized Linear Models
- Pattern Recognition and Neural Networks
- Bayesian Data Analysis
- Advances in neural information processing systems 7
- Spline Models for Observational Data.
- STATISTICS FOR SPATIAL DATA
- Bayesian Learning for Neural Networks
- Spline Models for Observational Data
- Generalized Linear Models