PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // NeuralNet.h 00004 // Copyright (c) 1998-2002 Pascal Vincent 00005 // Copyright (C) 1999-2002 Yoshua Bengio and University of Montreal 00006 // Copyright (c) 2002 Jean-Sebastien Senecal, Xavier Saint-Mleux, Rejean Ducharme 00007 // 00008 // Redistribution and use in source and binary forms, with or without 00009 // modification, are permitted provided that the following conditions are met: 00010 // 00011 // 1. Redistributions of source code must retain the above copyright 00012 // notice, this list of conditions and the following disclaimer. 00013 // 00014 // 2. Redistributions in binary form must reproduce the above copyright 00015 // notice, this list of conditions and the following disclaimer in the 00016 // documentation and/or other materials provided with the distribution. 00017 // 00018 // 3. The name of the authors may not be used to endorse or promote 00019 // products derived from this software without specific prior written 00020 // permission. 00021 // 00022 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR 00023 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES 00024 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN 00025 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 00026 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED 00027 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 00028 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 00029 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 00030 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 00031 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 00032 // 00033 // This file is part of the PLearn library. For more information on the PLearn 00034 // library, go to the PLearn Web site at www.plearn.org 00035 00036 00037 /* ******************************************************* 00038 * $Id: NeuralNet.h 8321 2007-11-28 21:37:09Z nouiz $ 00039 ******************************************************* */ 00040 00041 00042 #ifndef NeuralNet_INC 00043 #define NeuralNet_INC 00044 00045 #include "Learner.h" 00046 #include <plearn/opt/Optimizer.h> 00047 //#include "Var_all.h" 00048 00049 namespace PLearn { 00050 using namespace std; 00051 00055 class NeuralNet: public Learner 00056 { 00057 protected: 00058 Var input; // Var(inputsize()) 00059 Var target; // Var(targetsize()-weightsize()) 00060 Var costweights; // Var(weightsize()) 00061 Var target_and_weights;// hconcat(target&costweights) 00062 Var w1; // bias and weights of first hidden layer 00063 Var w2; // bias and weights of second hidden layer 00064 Var wout; // bias and weights of output layer 00065 Var wdirect; // bias and weights for direct in-to-out connection 00066 00067 Var output; 00068 VarArray costs; // al costs of interest 00069 Var cost; // cost for one (input,target) 00070 00071 VarArray params; // all arameter input vars 00072 00073 Vec paramsvalues; // values of all parameters 00074 Vec initial_paramsvalues; 00075 00076 public: 00077 Func f; // input -> output 00078 Func costf; // input & target -> output & cost 00079 Func output_and_target_to_cost; // output & target -> cost 00080 00081 public: 00082 00083 typedef Learner inherited; 00084 00085 // Build options inherited from learner: 00086 // inputsize, outputszie, targetsize, experiment_name, save_at_every_epoch 00087 00088 // Build options: 00089 int nhidden; // number of hidden units in first hidden layer (default:0) 00090 int nhidden2; // number of hidden units in second hidden layer (default:0) 00091 00092 real weight_decay; // default: 0 00093 real bias_decay; // default: 0 00094 real layer1_weight_decay; // default: MISSING_VALUE 00095 real layer1_bias_decay; // default: MISSING_VALUE 00096 real layer2_weight_decay; // default: MISSING_VALUE 00097 real layer2_bias_decay; // default: MISSING_VALUE 00098 real output_layer_weight_decay; // default: MISSING_VALUE 00099 real output_layer_bias_decay; // default: MISSING_VALUE 00100 real direct_in_to_out_weight_decay; // default: MISSING_VALUE 00101 00102 bool global_weight_decay; // default: false 00103 bool direct_in_to_out; // should we include direct input to output connecitons? default: false 00104 string output_transfer_func; // tanh, sigmoid, softplus, softmax (default: "" means no transfer function) 00105 int iseed; // seed for random nb generator, -1 = use time of day 00106 00108 // where the cost functions can be one of mse, mse_onehot, NLL, 00109 // class_error or multiclass_error (no default), or semisupervised_prob_class 00110 // (if the latter, then the semisupervised_flatten_factor option must be set). 00111 Array<string> cost_funcs; 00112 real semisupervised_flatten_factor; // see SemiSupervisedProbClassCostVariable for explanations 00113 Vec semisupervised_prior; // see SemiSupervisedProbClassCostVariable for explanations 00114 00115 // Build options related to the optimization: 00116 PP<Optimizer> optimizer; // the optimizer to use (no default) 00117 00118 int batch_size; // how many samples to use to estimate gradient before an update 00119 // 0 means the whole training set (default: 1) 00120 00121 int nepochs; // how many times the optimizer gets to see the training set (default: 10000). 00122 00123 string saveparams; // where to optionally save params after training 00124 00125 Array<Vec> normalization; 00126 private: 00127 void build_(); 00128 00129 public: 00130 00131 NeuralNet(); 00132 virtual ~NeuralNet(); 00133 PLEARN_DECLARE_OBJECT(NeuralNet); 00134 00135 // Learner methods 00136 00137 virtual void build(); 00138 virtual void forget(); // simply calls initializeParams() 00139 void initializeParams(); 00140 00141 virtual void train(VMat training_set); 00142 virtual void use(const Vec& inputvec, Vec& prediction); 00143 00144 virtual int costsize() const; 00145 virtual Array<string> costNames() const; 00146 virtual Array<string> testResultsNames() { return costNames(); } 00147 virtual void useAndCost(const Vec& inputvec, const Vec& targetvec, 00148 Vec outputvec, Vec costvec); 00149 void computeCost(const Vec& inputvec, const Vec& targetvec, 00150 const Vec& outputvec, const Vec& costvec); 00151 00152 virtual void makeDeepCopyFromShallowCopy(CopiesMap &copies); 00153 protected: 00154 static void declareOptions(OptionList& ol); 00155 00156 }; 00157 00158 DECLARE_OBJECT_PTR(NeuralNet); 00159 00160 } // end of namespace PLearn 00161 00162 #endif 00163 00164 00165 /* 00166 Local Variables: 00167 mode:c++ 00168 c-basic-offset:4 00169 c-file-style:"stroustrup" 00170 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00171 indent-tabs-mode:nil 00172 fill-column:79 00173 End: 00174 */ 00175 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :