rkdefinedic(3) [debian man page]

RKDEFINEDIC(3)						     Library Functions Manual						    RKDEFINEDIC(3)

NAME

       RkDefineDic - define specified candidates in the dictionary

SYNOPSIS

       #include <canna/RK.h>
       int RkDefineDic(cxnum, dicname, wordrec)
       int cxnum;
       char *dicname;
       char *wordrec;

DESCRIPTION

       RkDefineDic  defines  specified	candidates  in	the dictionary named by dicname.  Specify the word to add in the character string wordrec,
       which is written in the format:

	      reading	part-of-speech information   kanji candidate

       Writing wordrec, for example, as

	      (HIRAGANA)     #T35     (KANJI)  ...

       will specify a candidate whose part of speech #T35 is defined by the reading "(HIRAGANA)" and whose spelling matches "(KANJI)".

RETURN VALUE

       This function returns 0 if successful; otherwise it returns -1.	It also returns -1, without doing anything, if it has been run in  a  con-
       version mode context.

																    RKDEFINEDIC(3)

FANN_GET_CASCADE_NUM_CANDIDATES(3)					 1					FANN_GET_CASCADE_NUM_CANDIDATES(3)

fann_get_cascade_num_candidates - Returns the number of candidates used during training

SYNOPSIS

       int fann_get_cascade_num_candidates (resource  $ann)

DESCRIPTION

	The  number  of  candidates  used during training (calculated by multiplying fann_get_cascade_activation_functions_count(3), fann_get_cas-
       cade_activation_steepnesses_count(3) and fann_get_cascade_num_candidate_groups(3)).

	The actual candidates is defined by the fann_get_cascade_activation_functions(3)  and  fann_get_cascade_activation_steepnesses(3)  arrays.
       These arrays define the activation functions and activation steepnesses used for the candidate neurons. If there are 2 activation functions
       in the activation function array and 3 steepnesses in the steepness array, then there will be 2x3=6  different  candidates  which  will	be
       trained.  These	6  different candidates can be copied into several candidate groups, where the only difference between these groups is the
       initial weights. If the number of groups is set to 2, then the number of candidate neurons will be 2x3x2=12. The number of candidate groups
       is defined by fann_set_cascade_num_candidate_groups(3).

	The default number of candidates is 6x4x2 = 48

PARAMETERS

	      o $ann
		-Neural network resource.

RETURN VALUES

	The number of candidates used during training, or FALSE on error.

SEE ALSO

       fann_get_cascade_activation_functions(3),    fann_get_cascade_activation_functions_count(3),    fann_get_cascade_activation_steepnesses(3),
       fann_get_cascade_activation_steepnesses_count(3), fann_get_cascade_num_candidate_groups(3).

PHP Documentation Group 											FANN_GET_CASCADE_NUM_CANDIDATES(3)