include/dai/hak.h File Reference
Defines class HAK, which implements a variant of Generalized Belief Propagation.
More...
#include <string>
#include <dai/daialg.h>
#include <dai/regiongraph.h>
#include <dai/enum.h>
#include <dai/properties.h>
Go to the source code of this file.
|
Namespaces |
namespace | dai |
Classes |
class | dai::HAK |
| Approximate inference algorithm: implementation of single-loop ("Generalized Belief Propagation") and double-loop algorithms by Heskes, Albers and Kappen [HAK03]. More...
|
struct | dai::HAK::Properties |
| Parameters for HAK. More...
|
Detailed Description
Defines class HAK, which implements a variant of Generalized Belief Propagation.
- Idea:
- Implement more general region graphs and corresponding Generalized Belief Propagation updates as described in [YFW05].
- Todo:
- Use ClusterGraph instead of a vector<VarSet> for speed.
- Todo:
- Optimize this code for large factor graphs.
- Todo:
- Implement GBP parent-child algorithm.