GeneticAlgorithm.hpp

/*Copyright (c) 2019 Alexis Nasr && Franck Dary

 Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:i

 The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.

 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.*/
#ifndef GENETICALGORITHM__H
#define GENETICALGORITHM__H

#include <dynet/nodes.h>
#include <dynet/dynet.h>
#include <dynet/training.h>
#include <dynet/timing.h>
#include <dynet/expr.h>
#include <dynet/io.h>
#include <string>
#include <memory>
#include "NeuralNetwork.hpp"
#include "FeatureModel.hpp"
#include "MLPBase.hpp"

class GeneticAlgorithm : public NeuralNetwork
{
  private :

  /// @brief An Individual is a part of the current population.
  ///
  /// It can be evaluated against a particular metric, can mutate and reproduce with another of its kind.
  struct Individual
  {
    /// @brief A counter for giving unique id to objects of this struct.
    static int idCount;
    /// @brief The neural network corresponding to this Individual.
    MLPBase mlp;
    /// @brief The value of this Individual.
    ///
    /// This metric is used to dertermine wich are the best Individuals of the generation.
    /// For example it can be the inverse of the loss value of its MLP against the dev dataset.
    float value;
    /// @brief The loss of the MLP of this Individual.
    float loss;
    /// @brief Unique identifier for this individual.
    int id;
    /// @brief Create a new Individual from a certain topology.
    ///
    /// @param model The dynet model that will contains the mlp parameters.
    /// @param nbInputs The size of the mlp input layer.
    /// @param topology The desired topology for the mlp.
    /// @param nbOutputs The size of the mlp output layer..
    Individual(dynet::ParameterCollection & model, int nbInputs, const std::string & topology, int nbOutputs);
    /// @brief Create a blank individual, so that it will be loaded from a saved model.
    ///
    /// @param bestId The id of the individual that was saved in the file.
    Individual(unsigned int bestId);
    void becomeChildOf(Individual * other);
    void becomeChildOf(Individual * mom, Individual * dad);
    void mutate(float probability);
  };

  /// @brief The current generation.
  std::vector< std::unique_ptr<Individual> > generation;
  /// @brief The topology of the GeneticAlgorithm
  std::string topology;
  /// @brief The input layer size of the Individual's MLP.
  int nbInputs;
  /// @brief The output layer size of the Individual's MLP.
  int nbOutputs;

  private :

  /// @brief Load this GeneticAlgorithm from a file.
  ///
  /// @param filename The name of the file where the GeneticAlgorithm is stored.
  void load(const std::string & filename);
  /// @brief Get the value of an Individual depending on the loss of its MLP
  ///
  /// @param loss The loss of the MLP.
  ///
  /// @return  The value of the Individual.
  static float loss2value(float loss);

  public :

  /// @brief Create a new untrained GeneticAlgorithm from scratch.
  GeneticAlgorithm();

  /// @brief Create and load an already trained GeneticAlgorithm from a file.
  ///
  /// @param filename The file where the GeneticAlgorithm is stored.
  GeneticAlgorithm(const std::string & filename);

  /// @brief initialize a new untrained GeneticAlgorithm from a desired topology.
  ///
  /// @param nbInputs The size of the input.
  /// @param topology Description of the GeneticAlgorithm.
  /// @param nbOutputs The size of the output.
  void init(int nbInputs, const std::string & topology, int nbOutputs) override;

  /// @brief Give a score to each possible class, given an input.
  ///
  /// @param fd The input to use.
  ///
  /// @return A vector containing one score per possible class.
  std::vector<float> predict(FeatureModel::FeatureDescription & fd) override;

  /// @brief Update the parameters according to the given gold class.
  ///
  /// @param fd The input to use.
  /// @param gold The gold class of this input.
  ///
  /// @return The loss.
  float update(FeatureModel::FeatureDescription & fd, int gold) override;

  /// @brief Update the parameters according to the given gold vector.
  ///
  /// @param fd The input to use.
  /// @param gold The gold vector for this input.
  ///
  /// @return The loss.
  float update(FeatureModel::FeatureDescription & fd, const std::vector<float> & gold) override;

  /// @brief Get the loss according to the given gold class.
  ///
  /// @param fd The input to use.
  /// @param gold The gold class of this input.
  ///
  /// @return The loss.
  float getLoss(FeatureModel::FeatureDescription & fd, int gold) override;

  /// @brief Get the loss according to the given gold vector.
  ///
  /// @param fd The input to use.
  /// @param gold The gold vector for this input.
  ///
  /// @return The loss.
  float getLoss(FeatureModel::FeatureDescription & fd, const std::vector<float> & gold) override;

  /// @brief Save the GeneticAlgorithm to a file.
  /// 
  /// @param filename The file to write the GeneticAlgorithm to.
  void save(const std::string & filename) override;

  /// @brief Print the topology of the GeneticAlgorithm.
  ///
  /// @param output Where the topology will be printed.
  void printTopology(FILE * output) override;
  void endOfIteration() override;
};

#endif