This question already has an answer here:
Does Mathematica have any Bayesian optimization methods for learning hyper-parameters?
Practical Bayesian Optimization of Machine Learning Algorithms Jasper Snoek, Hugo Larochelle and Ryan P. Adams Advances in Neural Information Processing Systems, 2012
For example, I'm using Whetlab to learn parameters in a computer vision problem. But I'd like to use Mathematica, seems like something that should be supported with all of Version 9's support for gaussian processes right?
Here is an example of bayesian optimization at work: