PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // NnlmWordRepresentationLayer.h 00004 // 00005 // Copyright (C) 2006 Pierre-Antoine Manzagol 00006 // 00007 // Redistribution and use in source and binary forms, with or without 00008 // modification, are permitted provided that the following conditions are met: 00009 // 00010 // 1. Redistributions of source code must retain the above copyright 00011 // notice, this list of conditions and the following disclaimer. 00012 // 00013 // 2. Redistributions in binary form must reproduce the above copyright 00014 // notice, this list of conditions and the following disclaimer in the 00015 // documentation and/or other materials provided with the distribution. 00016 // 00017 // 3. The name of the authors may not be used to endorse or promote 00018 // products derived from this software without specific prior written 00019 // permission. 00020 // 00021 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR 00022 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES 00023 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN 00024 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 00025 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED 00026 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 00027 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 00028 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 00029 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 00030 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 00031 // 00032 // This file is part of the PLearn library. For more information on the PLearn 00033 // library, go to the PLearn Web site at www.plearn.org 00034 00035 // Authors: Pierre-Antoine Manzagol 00036 00040 #ifndef NnlmWordRepresentationLayer_INC 00041 #define NnlmWordRepresentationLayer_INC 00042 00043 #include <plearn/base/Object.h> 00044 #include <plearn/math/TMat_maths.h> 00045 #include <plearn_learners/online/OnlineLearningModule.h> 00046 00047 namespace PLearn { 00048 00066 class NnlmWordRepresentationLayer : public OnlineLearningModule 00067 { 00068 typedef OnlineLearningModule inherited; 00069 00070 public: 00071 //##### Public Build Options ############################################ 00072 00073 // NNLM related 00074 int vocabulary_size; 00075 int word_representation_size; 00076 int context_size; 00077 00080 real start_learning_rate; 00081 real decrease_constant; 00082 00083 00084 public: 00085 //##### Public Member Functions ######################################### 00086 00088 // ### Make sure the implementation in the .cc 00089 // ### initializes all fields to reasonable default values. 00090 NnlmWordRepresentationLayer(); 00091 00093 virtual void fprop(const Vec& input, Vec& output) const; 00094 00105 virtual void bpropUpdate(const Vec& input, const Vec& output, 00106 const Vec& output_gradient); 00107 00110 // virtual void bpropUpdate(const Vec& input, const Vec& output, 00111 // Vec& input_gradient, 00112 // const Vec& output_gradient); 00113 00123 // virtual void bbpropUpdate(const Vec& input, const Vec& output, 00124 // const Vec& output_gradient, 00125 // const Vec& output_diag_hessian); 00126 00130 // virtual void bbpropUpdate(const Vec& input, const Vec& output, 00131 // Vec& input_gradient, 00132 // const Vec& output_gradient, 00133 // Vec& input_diag_hessian, 00134 // const Vec& output_diag_hessian); 00135 00139 virtual void forget(); 00140 00141 00146 // virtual void finalize(); 00147 00150 // virtual bool bpropDoesNothing(); 00151 00152 //##### PLearn::Object Protocol ######################################### 00153 00154 // Declares other standard object methods. 00155 // ### If your class is not instantiatable (it has pure virtual methods) 00156 // ### you should replace this by PLEARN_DECLARE_ABSTRACT_OBJECT 00157 PLEARN_DECLARE_OBJECT(NnlmWordRepresentationLayer); 00158 00159 // Simply calls inherited::build() then build_() 00160 virtual void build(); 00161 00163 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00164 00165 protected: 00166 //##### Protected Options ############################################### 00167 00168 protected: 00169 //##### Protected Member Functions ###################################### 00170 virtual void resetWeights(); 00171 00173 static void declareOptions(OptionList& ol); 00174 00175 private: 00176 //##### Private Member Functions ######################################## 00177 00179 void build_(); 00180 00181 private: 00182 //##### Private Data Members ############################################ 00183 00184 int step_number; 00185 real learning_rate; 00186 00187 Mat weights; // NOT one neuron per line, bias first 00188 // Since we just do a lookup, one neuron per column, NO bias 00189 // matrix is vocabulary_size by word_representation_size 00190 00191 }; 00192 00193 // Declares a few other classes and functions related to this class 00194 DECLARE_OBJECT_PTR(NnlmWordRepresentationLayer); 00195 00196 } // end of namespace PLearn 00197 00198 #endif 00199 00200 00201 /* 00202 Local Variables: 00203 mode:c++ 00204 c-basic-offset:4 00205 c-file-style:"stroustrup" 00206 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00207 indent-tabs-mode:nil 00208 fill-column:79 00209 End: 00210 */ 00211 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :