next up previous contents
Next: Bayesian Probability Theory Up: Hierarchical Nonlinear Factor Analysis Previous: Learning Criteria

   
Bayesian Inference and Ensemble Learning

This chapter gives an overview of ensemble learning with emphasis on solutions yielding linear computational complexity. More comprehensive introductions to ensemble learning can be found for instance in [61,34,44].

In generative models, inference can be done by estimating how likely a set of parameter values could have produced the observed data. Basically one wants to find a representative of the probability mass in the parameter space, but there are different methods for doing it in practice.



 

Tapani Raiko
2001-12-10