conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm Class Reference

#include <CscNeuralNetworkGeneticAlgorithm.h>

Public Member Functions
	CscNeuralNetworkGeneticAlgorithm (unsigned nbGenerations, unsigned populationSize, unsigned nbInputs, unsigned nbOutputs, CscNeuralNetwork::DataSet *trainingDataSet, CscNeuralNetwork::DataSet *validationDataSet, unsigned copyPercentOfChance, unsigned crossoverPercentOfChance, unsigned mutationPercentOfChance, CscNeuralNetworkGeneticAlgorithmIndividualGenerator::AllPossibilitiesHyperparameters *allPossibilitiesHyperparameters)
virtual	~CscNeuralNetworkGeneticAlgorithm ()
const unsigned	getNbGenerations () const
const unsigned	getNbNeuralNetworkInputs () const
const unsigned	getNbNeuralNetworkOutputs () const
CscNeuralNetwork::DataSet *	getTrainingDataSet () const
CscNeuralNetwork::DataSet *	getValidationDataSet () const
CscNeuralNetworkGeneticAlgorithmGenerationGenerator *	getGenerationGenerator () const
CscNeuralNetworkTensorFlow *	launchGeneticAlgorithm ()
	Launches the genetic algorithm to generate neural network configurations. More...

Constructor & Destructor Documentation

CscNeuralNetworkGeneticAlgorithm()

conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::CscNeuralNetworkGeneticAlgorithm	(	unsigned	nbGenerations,
		unsigned	populationSize,
		unsigned	nbInputs,
		unsigned	nbOutputs,
		CscNeuralNetwork::DataSet *	trainingDataSet,
		CscNeuralNetwork::DataSet *	validationDataSet,
		unsigned	copyPercentOfChance,
		unsigned	crossoverPercentOfChance,
		unsigned	mutationPercentOfChance,
		CscNeuralNetworkGeneticAlgorithmIndividualGenerator::AllPossibilitiesHyperparameters *	allPossibilitiesHyperparameters
	)

~CscNeuralNetworkGeneticAlgorithm()

conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::~CscNeuralNetworkGeneticAlgorithm ( )

virtual

Member Function Documentation

getGenerationGenerator()

CscNeuralNetworkGeneticAlgorithmGenerationGenerator * conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::getGenerationGenerator

(

)

const

getNbGenerations()

const unsigned conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::getNbGenerations

(

)

const

getNbNeuralNetworkInputs()

const unsigned conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::getNbNeuralNetworkInputs

(

)

const

getNbNeuralNetworkOutputs()

const unsigned conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::getNbNeuralNetworkOutputs

(

)

const

getTrainingDataSet()

CscNeuralNetwork::DataSet * conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::getTrainingDataSet

(

)

const

getValidationDataSet()

CscNeuralNetwork::DataSet * conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::getValidationDataSet

(

)

const

launchGeneticAlgorithm()

CscNeuralNetworkTensorFlow * conscience_core::ai::nn::CscNeuralNetworkGeneticAlgorithm::launchGeneticAlgorithm

(

)

Launches the genetic algorithm to generate neural network configurations.

This method initiates and runs a genetic algorithm to create and optimize neural network configurations over multiple generations. The process involves generating an initial population randomly, evaluating their performance, and iteratively producing new generations by selecting and modifying the best performers.

Returns

CscNeuralNetworkTensorFlow* Pointer to the best neural network configuration found.

Exceptions

std::exception

If an error occurs during the execution of the genetic algorithm, a nullptr is returned and an error is logged.

The genetic algorithm process is as follows:

1. Randomly create the first generation.
2. Evaluate and sort the population based on their performance.
3. Iteratively create new generations and evaluate their performance until the desired number of generations is reached.
4. Return the best neural network configuration from the final generation.

---

The documentation for this class was generated from the following files:

• ArtificialIntelligence/CscNeuralNetworkGeneticAlgorithm.h
• ArtificialIntelligence/CscNeuralNetworkGeneticAlgorithm.cpp