Connectionists: Matlab code for Gaussian process prediction

[Carl Edward Rasmussen]

We would like to announce the availability of matlab code implementing the
main algorithms from our recent book "Gaussian Processes for Machine Learning"
from MIT Press. The code is available via:

    http://www.GaussianProcess.org/gpml

The programs implement regression and classification. Standard
regression as well as some sparse approximations are provided. Binary
classification is implemented using both the Laplace approximation and
the Expectation Propagation algorithm. The code supports a variety of
different covariance functions and learning of hyperparamters using
the marginal likelihood. Demo scripts are provided to illustrate
the use of the functions.

    Carl Edward Rasmussen & Chris Williams