demo20.cpp File Reference

Example 20: Retreating Sequential Search. More...

#include <boost/smart_ptr.hpp>
#include <exception>
#include <iostream>
#include <cstdlib>
#include <string>
#include <vector>
#include "error.hpp"
#include "global.hpp"
#include "subset.hpp"
#include "data_intervaller.hpp"
#include "data_splitter.hpp"
#include "data_splitter_5050.hpp"
#include "data_splitter_cv.hpp"
#include "data_splitter_leave1out.hpp"
#include "data_scaler.hpp"
#include "data_scaler_void.hpp"
#include "data_accessor_splitting_memTRN.hpp"
#include "data_accessor_splitting_memARFF.hpp"
#include "criterion_wrapper.hpp"
#include "distance_euclid.hpp"
#include "classifier_knn.hpp"
#include "seq_step_straight.hpp"
#include "search_seq_sfrs.hpp"

Include dependency graph for demo20.cpp:

Functions
int	main ()

---

Detailed Description

Example 20: Retreating Sequential Search.

---

Function Documentation

int main

(

)

Example 20: Retreating Sequential Search.

Retreating Search (SFRS or SBRS) is closely related to SFFS, but more thorough and slower. It evaluates more candidate subsets due to more excessive backtracking. This may be advantageous especially in case of SFRS which thus evaluates more of lower-dimensional potential solutions. See Example 52t: (Threaded SFRS) Result regularization using secondary criterion. for a result regularizing scenario for which SFRS is particularly suitable. In this example features are selected using SFRS algorithm and 3-NN wrapper classification accuracy as FS criterion. Classification accuracy (i.e, FS wrapper criterion value) is estimated on the first 50% of data samples by means of Leave-One-Out estimation. The final classification performance on the selected subspace is eventually validated on the second 50% of data. SFRS is primarily a d-optimizing procedure, thus it should be invoked with parameter 0 in search(0,...).

References FST::Search_SFRS< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, EVALUATOR >::get_result(), FST::Search_SFRS< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, EVALUATOR >::search(), FST::Search< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >::set_output_detail(), and FST::Search_SFRS< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, EVALUATOR >::set_search_direction().