SmartEngine  1.6.0
Classes | Public Member Functions | Properties | List of all members
SmartEngine.NeuralNetworks.GeneticTrainer Class Reference

Standard instance of IGeneticTrainer. More...

Inheritance diagram for SmartEngine.NeuralNetworks.GeneticTrainer:
SmartEngine.NeuralNetworks.LossTrainer SmartEngine.NeuralNetworks.IGeneticTrainer SmartEngine.Resource SmartEngine.ISerializable SmartEngine.Object SmartEngine.ISerializable SmartEngine.Disposable

Classes

class  CInfo
 Constructor info More...
 

Public Member Functions

 GeneticTrainer (CInfo cinfo)
 
void Initialize (NeuralNetworks.GeneticTrainerInitializationInfo info)
 IGeneticTrainer implementation. More...
 
void Step ()
 IGeneticTrainer implementation. More...
 
void SortPopulation ()
 IGeneticTrainer implementation. More...
 
int GetChromosomeLastIndex (int index)
 IGeneticTrainer implementation. More...
 
void SetChromosome (int index)
 IGeneticTrainer implementation. More...
 
void SetBestChromosome ()
 IGeneticTrainer implementation. More...
 
void CopyOutChromosome (int index, Graph graph)
 IGeneticTrainer implementation. More...
 
void CopyOutBestChromosome (Graph graph)
 IGeneticTrainer implementation. More...
 
void CopyOutTopAverage (float count, Graph graph, bool weightedAverage)
 IGeneticTrainer implementation. More...
 
void SetTrainingInfo (NeuralNetworks.GeneticTrainingInfo info)
 IGeneticTrainer implementation. More...
 
float GetLoss (int index)
 IGeneticTrainer implementation. More...
 
void SetLoss (int index, float loss)
 IGeneticTrainer implementation. More...
 
- Public Member Functions inherited from SmartEngine.NeuralNetworks.LossTrainer
unsafe void SetTrainingMethod (SmartEngine.NeuralNetworks.LossTrainingMethodInfo info)
 Sets the training method and associated parameters More...
 
- Public Member Functions inherited from SmartEngine.Resource
SerializationResult Load (string appendName=null)
 Load this object from disk. More...
 
SerializationResult Save (string appendName=null)
 Save this object to disk. More...
 
SerializationResult Serialize (MemoryBuffer buffer)
 Write the contents of this object to a buffer. More...
 
SerializationResult Serialize (out byte[] data)
 Write the contents of this object to a byte array. More...
 
SerializationResult Deserialize (MemoryBuffer buffer)
 Fill this object with contents from a buffer. More...
 
SerializationResult Deserialize (byte[] data)
 Fill this object with contents from a byte array. More...
 
- Public Member Functions inherited from SmartEngine.Object
void AddRef ()
 Increments the internal reference count on this object. It is not common to use this method directly. More...
 
void Release ()
 Decrements the internal reference count on this object. It is not common to use this method directly. More...
 
- Public Member Functions inherited from SmartEngine.Disposable
void Dispose ()
 Cleans up any internal state. It is not safe to use an object after it has been disposed. More...
 
- Public Member Functions inherited from SmartEngine.NeuralNetworks.IGeneticTrainer
void Initialize (GeneticTrainerInitializationInfo info)
 Initializes the newtwork with a new population. Not necessary to call if deserializing from disk. More...
 
void SetTrainingMethod (LossTrainingMethodInfo info)
 Sets the training method and associated parameters More...
 
void SetTrainingInfo (GeneticTrainingInfo info)
 Sets the genetic parameters of the trainer. More...
 
SerializationResult Load (string appendName=null)
 Load this object from disk. More...
 
SerializationResult Save (string appendName=null)
 Save this object to disk. More...
 

Properties

int PopulationCount [get]
 IGeneticTrainer implementation. More...
 
float MutationStandardDeviation [get]
 IGeneticTrainer implementation. More...
 
- Properties inherited from SmartEngine.NeuralNetworks.LossTrainer
uint GenerationCount [get]
 Returns the number of generations we have been training for. More...
 
float Loss [get]
 Returns the loss in the graph. More...
 
- Properties inherited from SmartEngine.Resource
string ResourceName [get]
 Returns the name of this resource passed to the constructor. More...
 
SerializationResult LastLoadResult [get]
 Returns the result of the last call to Load(). Useful for checking loaded data state after creation. More...
 
- Properties inherited from SmartEngine.NeuralNetworks.IGeneticTrainer
string ResourceName [get]
 Returns the name of this resource passed to the constructor. More...
 
uint GenerationCount [get]
 Returns the number of generations we have been training for. More...
 
float Loss [get]
 Returns the loss in the graph. More...
 
int PopulationCount [get]
 Retrieves the total number of chromosomes (test subjects) in the population. More...
 
float MutationStandardDeviation [get]
 Returns the current mutation standard deviation, taking into account adaptive behavior More...
 

Detailed Description

Standard instance of IGeneticTrainer.

Member Function Documentation

◆ CopyOutBestChromosome()

void SmartEngine.NeuralNetworks.GeneticTrainer.CopyOutBestChromosome ( Graph  graph)

◆ CopyOutChromosome()

void SmartEngine.NeuralNetworks.GeneticTrainer.CopyOutChromosome ( int  index,
Graph  graph 
)

◆ CopyOutTopAverage()

void SmartEngine.NeuralNetworks.GeneticTrainer.CopyOutTopAverage ( float  count,
Graph  graph,
bool  weightedAverage 
)

◆ GetChromosomeLastIndex()

int SmartEngine.NeuralNetworks.GeneticTrainer.GetChromosomeLastIndex ( int  index)

◆ GetLoss()

float SmartEngine.NeuralNetworks.GeneticTrainer.GetLoss ( int  index)

◆ Initialize()

void SmartEngine.NeuralNetworks.GeneticTrainer.Initialize ( NeuralNetworks.GeneticTrainerInitializationInfo  info)

IGeneticTrainer implementation.

◆ SetBestChromosome()

void SmartEngine.NeuralNetworks.GeneticTrainer.SetBestChromosome ( )

◆ SetChromosome()

void SmartEngine.NeuralNetworks.GeneticTrainer.SetChromosome ( int  index)

◆ SetLoss()

void SmartEngine.NeuralNetworks.GeneticTrainer.SetLoss ( int  index,
float  loss 
)

◆ SetTrainingInfo()

void SmartEngine.NeuralNetworks.GeneticTrainer.SetTrainingInfo ( NeuralNetworks.GeneticTrainingInfo  info)

IGeneticTrainer implementation.

◆ SortPopulation()

void SmartEngine.NeuralNetworks.GeneticTrainer.SortPopulation ( )

◆ Step()

void SmartEngine.NeuralNetworks.GeneticTrainer.Step ( )

Property Documentation

◆ MutationStandardDeviation

float SmartEngine.NeuralNetworks.GeneticTrainer.MutationStandardDeviation
get

IGeneticTrainer implementation.

◆ PopulationCount

int SmartEngine.NeuralNetworks.GeneticTrainer.PopulationCount
get

IGeneticTrainer implementation.