Feature Selection ToolboxFST3 Library / Documentation

FST::Search_Branch_And_Bound_Basic< RETURNTYPE, DIMTYPE, SUBSET, CRITERION > Class Template Reference

Implements Branch and Bound Basic method, i.e., with randomized node ordering. More...

#include <search_branch_and_bound_basic.hpp>

Inheritance diagram for FST::Search_Branch_And_Bound_Basic< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >:
Collaboration diagram for FST::Search_Branch_And_Bound_Basic< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >:

List of all members.

Public Types

typedef
Search_Branch_And_Bound
< RETURNTYPE, DIMTYPE, SUBSET,
CRITERION > 
parent
typedef parent::PCriterion PCriterion
typedef parent::PSubset PSubset
typedef parent::PNode PNode
typedef parent::Node Node
typedef parent::NodeType NodeType

Public Member Functions

virtual std::ostream & print (std::ostream &os) const

Protected Member Functions

virtual void initialize (const DIMTYPE d, const DIMTYPE n, const PCriterion crit)
 called before search - enables set-up of additional structures in descendants
virtual void pre_evaluate_availables ()
 assign values to each feature in availables - to be used for node ordering
virtual void post_process_tree_level ()
 enables to substitute missing COMPUTED values in nodes just after level creation, if needed
virtual bool cut_possible ()
 tests current node for the possibility to cut its sub-branch

Detailed Description

template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>
class FST::Search_Branch_And_Bound_Basic< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >

Implements Branch and Bound Basic method, i.e., with randomized node ordering.

BBB is the simplest and generally slowest of all B&B algorithms.

Note:
All Branch & Bound algorithms by definition yield the solution with the same maximum criterion value, therefore the main concern regarding particular Branch & Bound algorithm is only its search speed.
Due to possibly high number of subsets to be tested expect excessive computational time.
Result tracking in case of Branch & Bound algorithms records only results of target cardinality.

The documentation for this class was generated from the following file:

Generated on Thu Mar 31 11:38:49 2011 for FST3Library by  doxygen 1.6.1