Class ANN_Network

Description
  • access: public

Located in /Network.php (line 51)

ANN_Filesystem
   |
   --ANN_Network
Class Constant Summary
Method Summary
[629]   protected   static   string :  getDefaultFilename ()
[965]   public   static   void :  loadFromFile ([string $strFilename = null])
[1211]   public   static   ANN_Network :  loadFromHost (string $strUsername, string $strPassword, string $strHost)
[112]   public   ANN_Network :  __construct ([integer $intNumberOfHiddenLayers = 1], [integer $intNumberOfNeuronsPerLayer = 6], [integer $intNumberOfOutputs = 1])
[328]   protected   void :  activate ()
[292]   protected   void :  createHiddenLayers (integer $intNumberOfHiddenLayers, integer $intNumberOfNeuronsPerLayer)
[317]   protected   void :  createOutputLayer (integer $intNumberOfOutputs)
[1241]   protected   void :  detectOutputType ()
[589]   protected   integer :  getCountInputs ()
[1129]   protected   float :  getNetworkError ()
[437]   protected   integer :  getNextIndexInputsToTrain ([boolean $boolReset = FALSE])
[1004]   public   integer :  getNumberHiddenLayers ()
[1016]   public   integer :  getNumberHiddens ()
[991]   public   integer :  getNumberInputs ()
[1029]   public   integer :  getNumberOutputs ()
[234]   public   array :  getOutputs ()
[270]   public   array :  getOutputsByInputKey (integer $intKeyInput)
[464]   public   integer :  getTotalLoops ()
[427]   protected   boolean :  hasTimeLeftForTraining ()
[473]   protected   boolean :  isEpoch ()
[513]   protected   boolean :  isTrainingComplete ()
[543]   protected   boolean :  isTrainingCompleteByEpoch ()
[558]   protected   boolean :  isTrainingCompleteByInputKey (integer $intKeyInput)
[1113]   protected   void :  logNetworkErrors ()
[1062]   public   void :  logNetworkErrorsToFile (string $strFilename)
[1078]   protected   void :  logWeights ()
[1045]   public   void :  logWeightsToFile (string $strFilename)
[667]   public   void :  printNetwork ([integer $intLevel = 2])
[733]   protected   void :  printNetworkDetails1 ()
[847]   protected   void :  printNetworkDetails2 ()
[979]   public   void :  saveToFile ([string $strFilename = null])
[1183]   public   void :  saveToHost (string $strUsername, string $strPassword, string $strHost)
[140]   protected   void :  setInputs (array $arrInputs)
[213]   protected   void :  setInputsToTrain (array $arrInputs)
[497]   public   void :  setLearningRate ([float $floatLearningRate = 0.7])
[940]   protected   void :  setMaxExecutionTime ()
[1275]   public   void :  setMomentum ([float $floatMomentum = 0.95])
[1261]   public   void :  setOutputErrorTolerance ([float $floatOutputErrorTolerance = 0.02])
[162]   protected   void :  setOutputs (array $arrOutputs)
[640]   protected   void :  setOutputType ([integer $intType = self::OUTPUT_LINEAR])
[201]   public   void :  setValues (ANN_Values $objValues)
[360]   public   boolean :  train ()
[1150]   public   ANN_Network :  trainByHost (string $strUsername, string $strPassword, string $strHost)
[606]   protected   void :  training (array $arrOutputs)
[952]   public   void :  __wakeup ()
Methods
protected static string getDefaultFilename () [629]
  • return: Filename
  • access: protected
public static void loadFromFile ([string $strFilename = null]) [965]
  • string $strFilename: (Default: null)

Redefinition of:
ANN_Filesystem::loadFromFile()
public static ANN_Network loadFromHost (string $strUsername, string $strPassword, string $strHost) [1211]
  • throws: ANN_Exception
  • access: public
  • string $strUsername
  • string $strPassword
  • string $strHost
public  ANN_Network __construct ([integer $intNumberOfHiddenLayers = 1], [integer $intNumberOfNeuronsPerLayer = 6], [integer $intNumberOfOutputs = 1]) [112]
  • integer $intNumberOfHiddenLayers: (Default: 1)
  • integer $intNumberOfNeuronsPerLayer: (Default: 6)
  • integer $intNumberOfOutputs: (Default: 1)
protected  void activate () [328]
protected  void createHiddenLayers (integer $intNumberOfHiddenLayers, integer $intNumberOfNeuronsPerLayer) [292]
  • integer $intNumberOfHiddenLayers
  • integer $intNumberOfNeuronsPerLayer
protected  void createOutputLayer (integer $intNumberOfOutputs) [317]
  • integer $intNumberOfOutputs
protected  void detectOutputType () [1241]
protected  integer getCountInputs () [589]
protected  float getNetworkError () [1129]
protected  integer getNextIndexInputsToTrain ([boolean $boolReset = FALSE]) [437]
  • boolean $boolReset: (Default: FALSE)
public  integer getNumberHiddenLayers () [1004]
public  integer getNumberHiddens () [1016]
public  integer getNumberInputs () [991]
public  integer getNumberOutputs () [1029]
public  array getOutputs () [234]

Get the output values

Get the output values to the related input values set by setValues(). This method returns the output values as a two-dimensional array.

public  array getOutputsByInputKey (integer $intKeyInput) [270]
  • integer $intKeyInput
public  integer getTotalLoops () [464]
  • access: public
protected  boolean hasTimeLeftForTraining () [427]
protected  boolean isEpoch () [473]
protected  boolean isTrainingComplete () [513]
protected  boolean isTrainingCompleteByEpoch () [543]
protected  boolean isTrainingCompleteByInputKey (integer $intKeyInput) [558]
  • integer $intKeyInput
protected  void logNetworkErrors () [1113]
public  void logNetworkErrorsToFile (string $strFilename) [1062]

Log network errors while training in CSV format

  • string $strFilename
protected  void logWeights () [1078]
public  void logWeightsToFile (string $strFilename) [1045]

Log weights while training in CSV format

  • string $strFilename
public  void printNetwork ([integer $intLevel = 2]) [667]
  • integer $intLevel: (0, 1, 2) (Default: 2)
protected  void printNetworkDetails1 () [733]
protected  void printNetworkDetails2 () [847]
public  void saveToFile ([string $strFilename = null]) [979]
  • string $strFilename: (Default: null)

Redefinition of:
ANN_Filesystem::saveToFile()
public  void saveToHost (string $strUsername, string $strPassword, string $strHost) [1183]
  • throws: ANN_Exception
  • access: public
  • string $strUsername
  • string $strPassword
  • string $strHost
protected  void setInputs (array $arrInputs) [140]
  • array $arrInputs
protected  void setInputsToTrain (array $arrInputs) [213]
  • array $arrInputs
public  void setLearningRate ([float $floatLearningRate = 0.7]) [497]

Setting the learning rate

  • throws: ANN_Exception
  • access: public
  • uses: ANN_Exception::__construct()
  • float $floatLearningRate: (Default: 0.7) (0.1 .. 0.9)
protected  void setMaxExecutionTime () [940]
public  void setMomentum ([float $floatMomentum = 0.95]) [1275]
  • throws: ANN_Exception
  • access: public
  • uses: ANN_Exception::__construct()
  • float $floatMomentum: (Default: 0.95) (0 .. 1)
public  void setOutputErrorTolerance ([float $floatOutputErrorTolerance = 0.02]) [1261]

Setting the percentage of output error in comparison to the desired output

  • access: public
  • float $floatOutputErrorTolerance: (Default: 0.02)
protected  void setOutputs (array $arrOutputs) [162]
  • array $arrOutputs
protected  void setOutputType ([integer $intType = self::OUTPUT_LINEAR]) [640]
  • integer $intType: (Default: ANN_Network::OUTPUT_LINEAR)
public  void setValues (ANN_Values $objValues) [201]

Set Values for training or using network

Set Values of inputs and outputs for training or just inputs for using already trained network.

  1.  $objNetwork new ANN_Network(241);
  2.  
  3.  $objValues new ANN_Values;
  4.  
  5.  $objValues->train()
  6.            ->input(0.120.110.15)
  7.            ->output(0.56);
  8.  
  9.  $objNetwork->setValues($objValues);

public  ANN_Network trainByHost (string $strUsername, string $strPassword, string $strHost) [1150]
  • throws: ANN_Exception
  • access: public
  • string $strUsername
  • string $strPassword
  • string $strHost
protected  void training (array $arrOutputs) [606]
  • array $arrOutputs
public  void __wakeup () [952]

Inherited Methods

Inherited From ANN_Filesystem

ANN_Filesystem::loadFromFile()
ANN_Filesystem::saveToFile()
Class Constants
OUTPUT_BINARY = 2 (line 99)

Binary output type

OUTPUT_LINEAR = 1 (line 93)

Linear output type

Documentation generated on Mon, 23 May 2011 23:06:11 +0200 by phpDocumentor 1.4.1