Other software that way be useful for implementing Gaussian process models:
package by Ian
Nabney includes code for Gaussian process regression and many
other useful thing, . optimisers.
See Tom Minka 's
page on accelerating
matlab and his lightspeed
Seeger shares his code
for Kernel Multiple Logistic Regression, Incomplete Cholesky
Factorization and Low-rank Updates of Cholesky Factorizations.
See the software section of - .
Below is a collection of papers relevant to learning in Gaussian process
models. The papers are ordered according to topic, with occational papers
occuring under multiple headings.
| Covariance Functions
| Model Selection
| Learning Curves
| Reinforcement Learning
| Other Topics
Several papers provide tutorial material suitable for a first introduction to
learning in Gaussian process models. These range from very short [ Williams 2002 ] over intermediate [ MacKay 1998 ], [ Williams 1999 ]
to the more elaborate [ Rasmussen and Williams
2006 ]. All of these require only a minimum of prerequisites in the form of
elementary probability theory and linear algebra.
D. J. C. MacKay.
Theory, Inference and Learning Algorithms .
Cambridge University Press, Cambridge, UK, 2003.
chapter 45 .
Comment: A short introduction to GPs, emphasizing the
relationships to paramteric models (RBF networks, neural networks,