Abstract | ||
---|---|---|
In recent years variational methods have become a popular tool for approximate inference and learning in a wide variety of proba- bilistic models. For each new application, however, it is currently necessary rst to derive the variational update equations, and then to implement them in application-specic code. Each of these steps is both time consuming and error prone. In this paper we describe a general purpose inference engine called VIBES ('Variational Infer- ence for Bayesian Networks') which allows a wide variety of proba- bilistic models to be implemented and solved variationally without recourse to coding. New models are specied either through a simple script or via a graphical interface analogous to a drawing package. VIBES then automatically generates and solves the vari- ational equations. We illustrate the power and exibilit y of VIBES using examples from Bayesian mixture modelling. |
Year | Venue | Keywords |
---|---|---|
2002 | NIPS | variational method,graphical interface,bayesian network |
Field | DocType | Citations |
Free energy principle,Computer science,Inference,Approximate inference,Bayesian network,Artificial intelligence,Inference engine,Probabilistic logic,Machine learning,Variational message passing,Bayesian probability | Conference | 39 |
PageRank | References | Authors |
10.71 | 4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Christopher M. Bishop | 1 | 3385 | 467.65 |
David J. Spiegelhalter | 2 | 340 | 206.59 |
John M. Winn | 3 | 704 | 56.66 |