File: svm_c_linear_trainer_abstract.h

package info (click to toggle)
mldemos 0.5.1-3
  • links: PTS, VCS
  • area: main
  • in suites: jessie, jessie-kfreebsd
  • size: 32,224 kB
  • ctags: 46,525
  • sloc: cpp: 306,887; ansic: 167,718; ml: 126; sh: 109; makefile: 2
file content (289 lines) | stat: -rw-r--r-- 10,057 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
// Copyright (C) 2010  Davis E. King (davis@dlib.net)
// License: Boost Software License   See LICENSE.txt for the full license.
#undef DLIB_SVM_C_LiNEAR_TRAINER_ABSTRACT_H__
#ifdef DLIB_SVM_C_LiNEAR_TRAINER_ABSTRACT_H__

#include "../matrix/matrix_abstract.h"
#include "../algs.h"
#include "function_abstract.h"
#include "kernel_abstract.h"
#include "sparse_kernel_abstract.h"

namespace dlib
{
    template <
        typename K 
        >
    class svm_c_linear_trainer
    {
        /*!
            REQUIREMENTS ON K 
                Is either linear_kernel or sparse_linear_kernel.  

            WHAT THIS OBJECT REPRESENTS
                This object represents a tool for training the C formulation of 
                a support vector machine.  It is optimized for the case where
                linear kernels are used.  


                In particular, it is implemented using the OCAS algorithm
                described in the following paper:
                    Optimized Cutting Plane Algorithm for Large-Scale Risk Minimization
                        Vojtech Franc, Soren Sonnenburg; Journal of Machine Learning 
                        Research, 10(Oct):2157--2192, 2009. 
        !*/

    public:
        typedef K kernel_type;
        typedef typename kernel_type::scalar_type scalar_type;
        typedef typename kernel_type::sample_type sample_type;
        typedef typename kernel_type::mem_manager_type mem_manager_type;
        typedef decision_function<kernel_type> trained_function_type;

        svm_c_linear_trainer (
        );
        /*!
            ensures
                - This object is properly initialized and ready to be used
                  to train a support vector machine.
                - #get_oca() == oca() (i.e. an instance of oca with default parameters) 
                - #get_c_class1() == 1
                - #get_c_class2() == 1
                - #get_epsilon() == 0.001
                - this object will not be verbose unless be_verbose() is called
                - #get_max_iterations() == 10000
                - #learns_nonnegative_weights() == false
        !*/

        explicit svm_c_linear_trainer (
            const scalar_type& C 
        );
        /*!
            requires
                - C > 0
            ensures
                - This object is properly initialized and ready to be used
                  to train a support vector machine.
                - #get_oca() == oca() (i.e. an instance of oca with default parameters) 
                - #get_c_class1() == C
                - #get_c_class2() == C
                - #get_epsilon() == 0.001
                - this object will not be verbose unless be_verbose() is called
                - #get_max_iterations() == 10000
                - #learns_nonnegative_weights() == false
        !*/

        void set_epsilon (
            scalar_type eps
        );
        /*!
            requires
                - eps > 0
            ensures
                - #get_epsilon() == eps 
        !*/

        const scalar_type get_epsilon (
        ) const;
        /*!
            ensures
                - returns the error epsilon that determines when training should stop.
                  Smaller values may result in a more accurate solution but take longer 
                  to execute.
        !*/

        void set_max_iterations (
            unsigned long max_iter
        );
        /*!
            ensures
                - #get_max_iterations() == max_iter
        !*/

        unsigned long get_max_iterations (
        ); 
        /*!
            ensures
                - returns the maximum number of iterations the SVM optimizer is allowed to
                  run before it is required to stop and return a result.
        !*/

        void be_verbose (
        );
        /*!
            ensures
                - This object will print status messages to standard out so that a 
                  user can observe the progress of the algorithm.
        !*/

        void be_quiet (
        );
        /*!
            ensures
                - this object will not print anything to standard out
        !*/

        void set_oca (
            const oca& item
        );
        /*!
            ensures
                - #get_oca() == item 
        !*/

        const oca get_oca (
        ) const;
        /*!
            ensures
                - returns a copy of the optimizer used to solve the SVM problem.  
        !*/

        const kernel_type get_kernel (
        ) const;
        /*!
            ensures
                - returns a copy of the kernel function in use by this object.  Since
                  the linear kernels don't have any parameters this function just
                  returns kernel_type()
        !*/

        bool learns_nonnegative_weights (
        ) const;
        /*!
            ensures
                - The output of training is a weight vector and a bias value.  These
                  two things define the resulting decision function.  That is, the
                  decision function simply takes the dot product between the learned
                  weight vector and a test sample, then subtracts the bias value.  
                  Therefore, if learns_nonnegative_weights() == true then the resulting
                  learned weight vector will always have non-negative entries.  The
                  bias value may still be negative though.
        !*/
       
        void set_learns_nonnegative_weights (
            bool value
        );
        /*!
            ensures
                - #learns_nonnegative_weights() == value
        !*/

        void set_c (
            scalar_type C 
        );
        /*!
            requires
                - C > 0
            ensures
                - #get_c_class1() == C 
                - #get_c_class2() == C 
        !*/

        const scalar_type get_c_class1 (
        ) const;
        /*!
            ensures
                - returns the SVM regularization parameter for the +1 class.  
                  It is the parameter that determines the trade off between
                  trying to fit the +1 training data exactly or allowing more errors 
                  but hopefully improving the generalization of the resulting 
                  classifier.  Larger values encourage exact fitting while 
                  smaller values of C may encourage better generalization. 
        !*/

        const scalar_type get_c_class2 (
        ) const;
        /*!
            ensures
                - returns the SVM regularization parameter for the -1 class.  
                  It is the parameter that determines the trade off between
                  trying to fit the -1 training data exactly or allowing more errors 
                  but hopefully improving the generalization of the resulting 
                  classifier.  Larger values encourage exact fitting while 
                  smaller values of C may encourage better generalization. 
        !*/

        void set_c_class1 (
            scalar_type C
        );
        /*!
            requires
                - C > 0
            ensures
                - #get_c_class1() == C
        !*/

        void set_c_class2 (
            scalar_type C
        );
        /*!
            requires
                - C > 0
            ensures
                - #get_c_class2() == C
        !*/

        template <
            typename in_sample_vector_type,
            typename in_scalar_vector_type
            >
        const decision_function<kernel_type> train (
            const in_sample_vector_type& x,
            const in_scalar_vector_type& y
        ) const;
        /*!
            requires
                - is_binary_classification_problem(x,y) == true
                - x == a matrix or something convertible to a matrix via vector_to_matrix().
                  Also, x should contain sample_type objects.
                - y == a matrix or something convertible to a matrix via vector_to_matrix().
                  Also, y should contain scalar_type objects.
            ensures
                - trains a C support vector classifier given the training samples in x and 
                  labels in y.  
                - returns a decision function F with the following properties:
                    - F.alpha.size() == 1
                    - F.basis_vectors.size() == 1
                    - F.alpha(0) == 1
                    - if (new_x is a sample predicted have +1 label) then
                        - F(new_x) >= 0
                    - else
                        - F(new_x) < 0
        !*/

        template <
            typename in_sample_vector_type,
            typename in_scalar_vector_type
            >
        const decision_function<kernel_type> train (
            const in_sample_vector_type& x,
            const in_scalar_vector_type& y,
            scalar_type& svm_objective
        ) const;
        /*!
            requires
                - is_binary_classification_problem(x,y) == true
                - x == a matrix or something convertible to a matrix via vector_to_matrix().
                  Also, x should contain sample_type objects.
                - y == a matrix or something convertible to a matrix via vector_to_matrix().
                  Also, y should contain scalar_type objects.
            ensures
                - trains a C support vector classifier given the training samples in x and 
                  labels in y.  
                - #svm_objective == the final value of the SVM objective function
                - returns a decision function F with the following properties:
                    - F.alpha.size() == 1
                    - F.basis_vectors.size() == 1
                    - F.alpha(0) == 1
                    - if (new_x is a sample predicted have +1 label) then
                        - F(new_x) >= 0
                    - else
                        - F(new_x) < 0
        !*/

    }; 

}

#endif // DLIB_SVM_C_LiNEAR_TRAINER_ABSTRACT_H__