// Class: ReadH6AONN5MEMLP
// Automatically generated by MethodBase::MakeClass
//

/* configuration options =====================================================

#GEN -*-*-*-*-*-*-*-*-*-*-*- general info -*-*-*-*-*-*-*-*-*-*-*-

Method         : MLP::H6AONN5MEMLP
TMVA Release   : 3.8.6         [198662]
ROOT Release   : 5.10/00       [330240]
Creator        : thompson
Date           : Tue Jan 22 16:29:09 2008
Host           : Linux patlx3.fnal.gov 2.4.21-37.ELsmp #1 SMP Wed Sep 28 12:13:44 CDT 2005 i686 i686 i386 GNU/Linux
Dir            : /data/cdf04/thompson/hww_1fb/hwwcdf6.1.4v3_43/Hww/TMVAAna
Training events: 22164


#OPT -*-*-*-*-*-*-*-*-*-*-*-*- options -*-*-*-*-*-*-*-*-*-*-*-*-

# Set by User:
V: "False" [Verbose mode]
NCycles: "1000" [Number of training cycles]
HiddenLayers: "N+1,N" [Specification of hidden layer architecture]
# Default:
D: "False" [use-decorrelated-variables flag (depreciated)]
Normalise: "True" [Normalise input variables]
VarTransform: "None" [Variable transformation method]
VarTransformType: "Signal" [Use signal or background events for var transform]
NbinsMVAPdf: "60" [Number of bins used to create MVA PDF]
NsmoothMVAPdf: "2" [Number of smoothing iterations for MVA PDF]
VerboseLevel: "Info" [Verbosity level]
H: "False" [Print classifier-specific help message]
CreateMVAPdfs: "False" [Create PDFs for classifier outputs]
TxtWeightFilesOnly: "True" [if True, write all weights as text files]
NeuronType: "sigmoid" [Neuron activation function type]
NeuronInputType: "sum" [Neuron input function type]
TrainingMethod: "BP" [Train with Back-Propagation (BP - default) or Genetic Algorithm (GA - slower and worse)]
LearningRate: "0.02" [ANN learning rate parameter]
DecayRate: "0.01" [Decay rate for learning parameter]
TestRate: "10" [Test for overtraining performed at each #th epochs]
BPMode: "sequential" [Back-propagation learning mode: sequential or batch]
BatchSize: "-1" [Batch size: number of events/batch, only set if in Batch Mode, -1 for BatchSize=number_of_events]
##


#VAR -*-*-*-*-*-*-*-*-*-*-*-* variables *-*-*-*-*-*-*-*-*-*-*-*-

NVar 11
LRHWW                         LRHWW                             'F'    [0,1]
LRWW                          LRWW                              'F'    [0,1.00408148766]
LRWg                          LRWg                              'F'    [0,0.99993622303]
LRWj                          LRWj                              'F'    [-0.00408143829554,1]
LRZZ                          LRZZ                              'F'    [0,1]
Met                           Met                               'F'    [15.0160713196,264.722930908]
MetDelPhi                     MetDelPhi                         'F'    [0.143834546208,3.13655138016]
MetSpec                       MetSpec                           'F'    [15.0028028488,188.142364502]
dPhiLeptons                   dPhiLeptons                       'F'    [3.69548797607e-05,3.14073061943]
dRLeptons                     dRLeptons                         'F'    [0.341997534037,4.52171230316]
dimass                        dimass                            'F'    [16.0177326202,652.247131348]


============================================================================ */

#include <vector>
#include <cmath>
#include <string>
#include <iostream>

#ifndef IClassifierReader__def
#define IClassifierReader__def

class IClassifierReader {

 public:

   // constructor
   IClassifierReader() {}
   virtual ~IClassifierReader() {}

   // return classifier response
   virtual double GetMvaValue( const std::vector<double>& inputValues ) const = 0;
};

#endif

class ReadH6AONN5MEMLP : public IClassifierReader {

 public:

   // constructor
   ReadH6AONN5MEMLP( std::vector<std::string>& theInputVars ) 
      : IClassifierReader(),
        fClassName( "ReadH6AONN5MEMLP" ),
        fStatusIsClean( true ),
        fNvars( 11 ),
        fIsNormalised( true )
   {      
      // the training input variables
      const char* inputVars[] = { "LRHWW", "LRWW", "LRWg", "LRWj", "LRZZ", "Met", "MetDelPhi", "MetSpec", "dPhiLeptons", "dRLeptons", "dimass" };

      // sanity checks
      if (theInputVars.size() <= 0) {
         std::cout << "Problem in class \"" << fClassName << "\": empty input vector" << std::endl;
         fStatusIsClean = false;
      }

      if (theInputVars.size() != fNvars) {
         std::cout << "Problem in class \"" << fClassName << "\": mismatch in number of input values: "
                   << theInputVars.size() << " != " << fNvars << std::endl;
         fStatusIsClean = false;
      }

      // validate input variables
      for (size_t ivar = 0; ivar < theInputVars.size(); ivar++) {
         if (theInputVars[ivar] != inputVars[ivar]) {
            std::cout << "Problem in class \"" << fClassName << "\": mismatch in input variable names" << std::endl
                      << " for variable [" << ivar << "]: " << theInputVars[ivar].c_str() << " != " << inputVars[ivar] << std::endl;
            fStatusIsClean = false;
         }
      }

      // initialize min and max vectors (for normalisation)
      fVmin[0] = 0;
      fVmax[0] = 1;
      fVmin[1] = 0;
      fVmax[1] = 1.00408148765564;
      fVmin[2] = 0;
      fVmax[2] = 0.99993622303009;
      fVmin[3] = -0.00408143829554319;
      fVmax[3] = 1;
      fVmin[4] = 0;
      fVmax[4] = 1;
      fVmin[5] = 15.0160713195801;
      fVmax[5] = 264.722930908203;
      fVmin[6] = 0.143834546208382;
      fVmax[6] = 3.13655138015747;
      fVmin[7] = 15.0028028488159;
      fVmax[7] = 188.142364501953;
      fVmin[8] = 3.69548797607422e-05;
      fVmax[8] = 3.14073061943054;
      fVmin[9] = 0.341997534036636;
      fVmax[9] = 4.52171230316162;
      fVmin[10] = 16.0177326202393;
      fVmax[10] = 652.247131347656;

      // initialize input variable types
      fType[0] = 'F';
      fType[1] = 'F';
      fType[2] = 'F';
      fType[3] = 'F';
      fType[4] = 'F';
      fType[5] = 'F';
      fType[6] = 'F';
      fType[7] = 'F';
      fType[8] = 'F';
      fType[9] = 'F';
      fType[10] = 'F';

      // initialize constants
      Initialize();

   }

   // destructor
   virtual ~ReadH6AONN5MEMLP() {
      Clear(); // method-specific
   }

   // the classifier response
   // "inputValues" is a vector of input values in the same order as the 
   // variables given to the constructor
   double GetMvaValue( const std::vector<double>& inputValues ) const
   {
      // classifier response value
      double retval = 0;

      // classifier response, sanity check first
      if (!fStatusIsClean) {
         std::cout << "Problem in class \"" << fClassName << "\": cannot return classifier response"
                   << " because status is dirty" << std::endl;
         retval = 0;
      }
      else {
         if (IsNormalised()) {
            // normalise variables
            std::vector<double> iV;
            int ivar = 0;
            for (std::vector<double>::const_iterator varIt = inputValues.begin();
                 varIt != inputValues.end(); varIt++, ivar++) {
               iV.push_back(NormVariable( *varIt, fVmin[ivar], fVmax[ivar] ));
            }
            retval = GetMvaValue__( iV );
         }
         else {
            retval = GetMvaValue__( inputValues );
         }
      }

      return retval;
   }

 private:

   // method-specific destructor
   void Clear();

   // common member variables
   const char* fClassName;
   bool fStatusIsClean;

   const size_t fNvars;
   size_t GetNvar()           const { return fNvars; }
   char   GetType( int ivar ) const { return fType[ivar]; }

   // normalisation of input variables
   const bool fIsNormalised;
   bool IsNormalised() const { return fIsNormalised; }
   double fVmin[11];
   double fVmax[11];
   double NormVariable( double x, double xmin, double xmax ) const {
      // normalise to output range: [-1, 1]
      return 2*(x - xmin)/(xmax - xmin) - 1.0;
   }

   // type of input variable: 'F' or 'I'
   char   fType[11];

   // initialize internal variables
   void Initialize();
   double GetMvaValue__( const std::vector<double>& inputValues ) const;

   // private members (method specific)

   double ActivationFnc(double x) const;

   int fLayers;
   int fLayerSize[4];
   double fWeightMatrix0to1[13][12];   // weight matrix from layer 0 to 1
   double fWeightMatrix1to2[12][13];   // weight matrix from layer 1 to 2
   double fWeightMatrix2to3[1][12];   // weight matrix from layer 2 to 3

   double * fWeights[4];
};

inline void ReadH6AONN5MEMLP::Initialize()
{
   // build network structure
   fLayers = 4;
   fLayerSize[0] = 12; fWeights[0] = new double[12]; 
   fLayerSize[1] = 13; fWeights[1] = new double[13]; 
   fLayerSize[2] = 12; fWeights[2] = new double[12]; 
   fLayerSize[3] = 1; fWeights[3] = new double[1]; 
   // weight matrix from layer 0 to 1
   fWeightMatrix0to1[0][0] = 0.613211447974565;
   fWeightMatrix0to1[1][0] = 1.19735516581711;
   fWeightMatrix0to1[2][0] = -0.284950773417979;
   fWeightMatrix0to1[3][0] = 2.02144896293521;
   fWeightMatrix0to1[4][0] = 0.526111480481461;
   fWeightMatrix0to1[5][0] = 2.06492356266353;
   fWeightMatrix0to1[6][0] = 2.32350540552265;
   fWeightMatrix0to1[7][0] = -0.127370742046864;
   fWeightMatrix0to1[8][0] = 0.534331513549976;
   fWeightMatrix0to1[9][0] = 1.41205858377097;
   fWeightMatrix0to1[10][0] = 1.52538981549126;
   fWeightMatrix0to1[11][0] = 0.493122096237733;
   fWeightMatrix0to1[0][1] = 1.84974108362766;
   fWeightMatrix0to1[1][1] = 0.607164692544204;
   fWeightMatrix0to1[2][1] = 1.11661798695218;
   fWeightMatrix0to1[3][1] = -1.37991731681077;
   fWeightMatrix0to1[4][1] = 1.35187033483004;
   fWeightMatrix0to1[5][1] = 0.0117102772851026;
   fWeightMatrix0to1[6][1] = -1.80587655580226;
   fWeightMatrix0to1[7][1] = 1.36216519095313;
   fWeightMatrix0to1[8][1] = 0.973902826937963;
   fWeightMatrix0to1[9][1] = 0.849953442059277;
   fWeightMatrix0to1[10][1] = 0.379670944850597;
   fWeightMatrix0to1[11][1] = -0.306962033395781;
   fWeightMatrix0to1[0][2] = 0.399610238744364;
   fWeightMatrix0to1[1][2] = 0.428430320365192;
   fWeightMatrix0to1[2][2] = 0.594175248012253;
   fWeightMatrix0to1[3][2] = -1.73371023772627;
   fWeightMatrix0to1[4][2] = 1.97215174750525;
   fWeightMatrix0to1[5][2] = 0.19059502836454;
   fWeightMatrix0to1[6][2] = -0.716052475019457;
   fWeightMatrix0to1[7][2] = -0.794407687673304;
   fWeightMatrix0to1[8][2] = -0.674840147095099;
   fWeightMatrix0to1[9][2] = -1.31996136902879;
   fWeightMatrix0to1[10][2] = -0.243628611619097;
   fWeightMatrix0to1[11][2] = 1.05899523435877;
   fWeightMatrix0to1[0][3] = 0.753997349618224;
   fWeightMatrix0to1[1][3] = 0.601533965732406;
   fWeightMatrix0to1[2][3] = 0.831262810531367;
   fWeightMatrix0to1[3][3] = 2.1146202325515;
   fWeightMatrix0to1[4][3] = -1.15030759062056;
   fWeightMatrix0to1[5][3] = -0.141248278227161;
   fWeightMatrix0to1[6][3] = -0.395360446329566;
   fWeightMatrix0to1[7][3] = -1.6829191205804;
   fWeightMatrix0to1[8][3] = -0.152786568771739;
   fWeightMatrix0to1[9][3] = -1.2122904995859;
   fWeightMatrix0to1[10][3] = -0.313415818273734;
   fWeightMatrix0to1[11][3] = 0.695698330850134;
   fWeightMatrix0to1[0][4] = 0.628028645647161;
   fWeightMatrix0to1[1][4] = 0.117681721214366;
   fWeightMatrix0to1[2][4] = 0.731592232922859;
   fWeightMatrix0to1[3][4] = -1.54404309253471;
   fWeightMatrix0to1[4][4] = -0.0715655741092681;
   fWeightMatrix0to1[5][4] = -1.49351053484489;
   fWeightMatrix0to1[6][4] = -0.235531936255798;
   fWeightMatrix0to1[7][4] = 0.283351892191331;
   fWeightMatrix0to1[8][4] = -0.343548842038701;
   fWeightMatrix0to1[9][4] = 0.532949446497238;
   fWeightMatrix0to1[10][4] = -0.530597754187149;
   fWeightMatrix0to1[11][4] = -0.0640064446847375;
   fWeightMatrix0to1[0][5] = -0.873592751255708;
   fWeightMatrix0to1[1][5] = -0.3022608856101;
   fWeightMatrix0to1[2][5] = -2.06230863140504;
   fWeightMatrix0to1[3][5] = 0.710933711047074;
   fWeightMatrix0to1[4][5] = 1.13514159782997;
   fWeightMatrix0to1[5][5] = -1.8936092635865;
   fWeightMatrix0to1[6][5] = 1.38575740152642;
   fWeightMatrix0to1[7][5] = -0.555099530999534;
   fWeightMatrix0to1[8][5] = -0.002414459197943;
   fWeightMatrix0to1[9][5] = 1.08065143529171;
   fWeightMatrix0to1[10][5] = -0.714398987929779;
   fWeightMatrix0to1[11][5] = -1.19192783024985;
   fWeightMatrix0to1[0][6] = -1.29568226279354;
   fWeightMatrix0to1[1][6] = -0.854528030293082;
   fWeightMatrix0to1[2][6] = 1.47058148877292;
   fWeightMatrix0to1[3][6] = -0.756176698128333;
   fWeightMatrix0to1[4][6] = -0.575581759839858;
   fWeightMatrix0to1[5][6] = -0.180505603448863;
   fWeightMatrix0to1[6][6] = -1.95936810110296;
   fWeightMatrix0to1[7][6] = 2.31656661601497;
   fWeightMatrix0to1[8][6] = -0.484163689345917;
   fWeightMatrix0to1[9][6] = -0.192101836225084;
   fWeightMatrix0to1[10][6] = 1.01691857498247;
   fWeightMatrix0to1[11][6] = 1.10245128175167;
   fWeightMatrix0to1[0][7] = -0.177823370439616;
   fWeightMatrix0to1[1][7] = 0.613962660046592;
   fWeightMatrix0to1[2][7] = 1.798679903031;
   fWeightMatrix0to1[3][7] = -0.468492026762919;
   fWeightMatrix0to1[4][7] = 1.29587451335024;
   fWeightMatrix0to1[5][7] = -0.0405904865757386;
   fWeightMatrix0to1[6][7] = 0.773335162750068;
   fWeightMatrix0to1[7][7] = -0.362793577711158;
   fWeightMatrix0to1[8][7] = -0.0522299535828192;
   fWeightMatrix0to1[9][7] = 1.91482587014237;
   fWeightMatrix0to1[10][7] = -2.11480681209309;
   fWeightMatrix0to1[11][7] = 2.12232070938685;
   fWeightMatrix0to1[0][8] = -0.464369613731379;
   fWeightMatrix0to1[1][8] = -0.829457337265395;
   fWeightMatrix0to1[2][8] = 2.08334686776067;
   fWeightMatrix0to1[3][8] = -2.0695967915939;
   fWeightMatrix0to1[4][8] = 0.638409531585905;
   fWeightMatrix0to1[5][8] = 0.539673366381435;
   fWeightMatrix0to1[6][8] = 0.547483744678437;
   fWeightMatrix0to1[7][8] = -1.5147734489714;
   fWeightMatrix0to1[8][8] = 2.80012165969375;
   fWeightMatrix0to1[9][8] = -0.336072113904179;
   fWeightMatrix0to1[10][8] = 0.582729844289055;
   fWeightMatrix0to1[11][8] = -0.778775457602973;
   fWeightMatrix0to1[0][9] = 0.404066275613526;
   fWeightMatrix0to1[1][9] = -2.95644467690105;
   fWeightMatrix0to1[2][9] = 1.79850461743867;
   fWeightMatrix0to1[3][9] = -1.23835233137084;
   fWeightMatrix0to1[4][9] = 0.585583206721445;
   fWeightMatrix0to1[5][9] = 0.512605124747172;
   fWeightMatrix0to1[6][9] = -0.156446608355927;
   fWeightMatrix0to1[7][9] = 0.016068656806824;
   fWeightMatrix0to1[8][9] = -0.476989590763905;
   fWeightMatrix0to1[9][9] = -2.22291625600311;
   fWeightMatrix0to1[10][9] = -0.89380528786807;
   fWeightMatrix0to1[11][9] = 0.331305708122069;
   fWeightMatrix0to1[0][10] = -0.788527307488516;
   fWeightMatrix0to1[1][10] = 0.697946493982259;
   fWeightMatrix0to1[2][10] = 1.58765059188586;
   fWeightMatrix0to1[3][10] = -1.66852208769396;
   fWeightMatrix0to1[4][10] = 1.14304144469938;
   fWeightMatrix0to1[5][10] = -1.74402271083579;
   fWeightMatrix0to1[6][10] = -1.8414916712973;
   fWeightMatrix0to1[7][10] = 0.183960529224865;
   fWeightMatrix0to1[8][10] = -0.427029194140254;
   fWeightMatrix0to1[9][10] = -0.504442466394742;
   fWeightMatrix0to1[10][10] = -1.19069091699479;
   fWeightMatrix0to1[11][10] = -1.61554772928758;
   fWeightMatrix0to1[0][11] = -1.38472974348894;
   fWeightMatrix0to1[1][11] = -0.142956180263834;
   fWeightMatrix0to1[2][11] = -0.624830824812566;
   fWeightMatrix0to1[3][11] = 0.988326596332867;
   fWeightMatrix0to1[4][11] = 0.884184294171006;
   fWeightMatrix0to1[5][11] = 1.53384927957735;
   fWeightMatrix0to1[6][11] = -0.144685889412332;
   fWeightMatrix0to1[7][11] = -0.917633068958881;
   fWeightMatrix0to1[8][11] = 2.20816487275575;
   fWeightMatrix0to1[9][11] = -1.94439837229924;
   fWeightMatrix0to1[10][11] = 0.0288639992994691;
   fWeightMatrix0to1[11][11] = -0.279190310800803;
   // weight matrix from layer 1 to 2
   fWeightMatrix1to2[0][0] = -1.62065223669388;
   fWeightMatrix1to2[1][0] = 0.108307387426092;
   fWeightMatrix1to2[2][0] = -0.880033062639659;
   fWeightMatrix1to2[3][0] = -0.871390091032661;
   fWeightMatrix1to2[4][0] = -1.9415738735622;
   fWeightMatrix1to2[5][0] = 0.850582028676234;
   fWeightMatrix1to2[6][0] = 1.56463733525027;
   fWeightMatrix1to2[7][0] = 1.62514442521981;
   fWeightMatrix1to2[8][0] = 1.66488231001733;
   fWeightMatrix1to2[9][0] = -2.07229722212258;
   fWeightMatrix1to2[10][0] = -0.681503815517453;
   fWeightMatrix1to2[0][1] = 0.819163889576295;
   fWeightMatrix1to2[1][1] = -1.85601080264611;
   fWeightMatrix1to2[2][1] = -1.03456235515161;
   fWeightMatrix1to2[3][1] = -0.0530571273269996;
   fWeightMatrix1to2[4][1] = 1.36953310861049;
   fWeightMatrix1to2[5][1] = -2.31313582851696;
   fWeightMatrix1to2[6][1] = -0.792069285656398;
   fWeightMatrix1to2[7][1] = 0.0405370848170548;
   fWeightMatrix1to2[8][1] = -1.45005213949101;
   fWeightMatrix1to2[9][1] = -1.32771772055874;
   fWeightMatrix1to2[10][1] = -0.649951035141543;
   fWeightMatrix1to2[0][2] = 0.499181422646766;
   fWeightMatrix1to2[1][2] = -0.225830161430845;
   fWeightMatrix1to2[2][2] = -0.868693333704599;
   fWeightMatrix1to2[3][2] = -0.123281995504986;
   fWeightMatrix1to2[4][2] = 1.52251699296038;
   fWeightMatrix1to2[5][2] = -0.269262729416618;
   fWeightMatrix1to2[6][2] = 0.990941550950125;
   fWeightMatrix1to2[7][2] = -1.97179099573198;
   fWeightMatrix1to2[8][2] = 0.55936785880395;
   fWeightMatrix1to2[9][2] = -0.222616364575549;
   fWeightMatrix1to2[10][2] = -0.0599358392800542;
   fWeightMatrix1to2[0][3] = -1.55060332530937;
   fWeightMatrix1to2[1][3] = 0.0745084788727896;
   fWeightMatrix1to2[2][3] = 0.753903415234065;
   fWeightMatrix1to2[3][3] = -2.29208511858721;
   fWeightMatrix1to2[4][3] = 0.9350907803128;
   fWeightMatrix1to2[5][3] = 0.0939830108695377;
   fWeightMatrix1to2[6][3] = 1.01124350689179;
   fWeightMatrix1to2[7][3] = 0.145202222986952;
   fWeightMatrix1to2[8][3] = -1.90444405451868;
   fWeightMatrix1to2[9][3] = -2.12554248970524;
   fWeightMatrix1to2[10][3] = -0.648603034060713;
   fWeightMatrix1to2[0][4] = 0.173894824650667;
   fWeightMatrix1to2[1][4] = 0.0145700454761646;
   fWeightMatrix1to2[2][4] = 0.15925581582096;
   fWeightMatrix1to2[3][4] = -0.945216654461261;
   fWeightMatrix1to2[4][4] = 1.1293766193435;
   fWeightMatrix1to2[5][4] = 0.79629982988128;
   fWeightMatrix1to2[6][4] = -1.34614573330032;
   fWeightMatrix1to2[7][4] = -0.132519281352992;
   fWeightMatrix1to2[8][4] = 1.13886264827561;
   fWeightMatrix1to2[9][4] = 0.671752612794543;
   fWeightMatrix1to2[10][4] = -0.638518123359932;
   fWeightMatrix1to2[0][5] = -0.793124708375802;
   fWeightMatrix1to2[1][5] = -0.117602012124577;
   fWeightMatrix1to2[2][5] = -0.437498681745087;
   fWeightMatrix1to2[3][5] = -0.790834649238869;
   fWeightMatrix1to2[4][5] = -2.19172654370689;
   fWeightMatrix1to2[5][5] = -1.23221361203798;
   fWeightMatrix1to2[6][5] = -1.01071529897712;
   fWeightMatrix1to2[7][5] = 0.196007443585614;
   fWeightMatrix1to2[8][5] = -1.87127472768271;
   fWeightMatrix1to2[9][5] = 1.4931307899727;
   fWeightMatrix1to2[10][5] = -1.02337662167422;
   fWeightMatrix1to2[0][6] = -1.18934805340973;
   fWeightMatrix1to2[1][6] = 1.00144309024076;
   fWeightMatrix1to2[2][6] = -1.7549709923021;
   fWeightMatrix1to2[3][6] = -1.92656173617329;
   fWeightMatrix1to2[4][6] = 1.06059389012167;
   fWeightMatrix1to2[5][6] = -0.867723776349739;
   fWeightMatrix1to2[6][6] = 0.410508682622565;
   fWeightMatrix1to2[7][6] = -2.50244568356428;
   fWeightMatrix1to2[8][6] = -1.03421777303862;
   fWeightMatrix1to2[9][6] = 0.807992471943973;
   fWeightMatrix1to2[10][6] = -3.05700374118392;
   fWeightMatrix1to2[0][7] = 0.841363645974351;
   fWeightMatrix1to2[1][7] = 0.0399899870335095;
   fWeightMatrix1to2[2][7] = -0.841100780000778;
   fWeightMatrix1to2[3][7] = -1.30648826219342;
   fWeightMatrix1to2[4][7] = -1.02037383373538;
   fWeightMatrix1to2[5][7] = -1.00595648877921;
   fWeightMatrix1to2[6][7] = -0.733190803096036;
   fWeightMatrix1to2[7][7] = -2.02323146567523;
   fWeightMatrix1to2[8][7] = -0.203709906629711;
   fWeightMatrix1to2[9][7] = -1.12974514224146;
   fWeightMatrix1to2[10][7] = 0.896938355877366;
   fWeightMatrix1to2[0][8] = -1.73009442841515;
   fWeightMatrix1to2[1][8] = -0.529596594821289;
   fWeightMatrix1to2[2][8] = 1.07419807131525;
   fWeightMatrix1to2[3][8] = 0.602882287824612;
   fWeightMatrix1to2[4][8] = -1.09188138167671;
   fWeightMatrix1to2[5][8] = 1.64986431158832;
   fWeightMatrix1to2[6][8] = -2.25090058672498;
   fWeightMatrix1to2[7][8] = 0.130191555635028;
   fWeightMatrix1to2[8][8] = -0.521951378468118;
   fWeightMatrix1to2[9][8] = -1.8423568521375;
   fWeightMatrix1to2[10][8] = 1.39814006526896;
   fWeightMatrix1to2[0][9] = -0.561376849309435;
   fWeightMatrix1to2[1][9] = 1.03361404898218;
   fWeightMatrix1to2[2][9] = 0.98309440975295;
   fWeightMatrix1to2[3][9] = 0.0523749107753963;
   fWeightMatrix1to2[4][9] = 1.80553442105013;
   fWeightMatrix1to2[5][9] = -1.40454340032232;
   fWeightMatrix1to2[6][9] = -1.23647328524511;
   fWeightMatrix1to2[7][9] = -0.712377458386237;
   fWeightMatrix1to2[8][9] = -0.598875320443104;
   fWeightMatrix1to2[9][9] = -1.25455445890062;
   fWeightMatrix1to2[10][9] = -0.35529210918877;
   fWeightMatrix1to2[0][10] = 0.617905878888438;
   fWeightMatrix1to2[1][10] = -0.98004154415098;
   fWeightMatrix1to2[2][10] = -2.17093375477283;
   fWeightMatrix1to2[3][10] = 1.12600440144648;
   fWeightMatrix1to2[4][10] = -1.02164483718247;
   fWeightMatrix1to2[5][10] = -1.24015508784935;
   fWeightMatrix1to2[6][10] = -1.23767055532727;
   fWeightMatrix1to2[7][10] = 0.193632341496243;
   fWeightMatrix1to2[8][10] = -0.250506091960279;
   fWeightMatrix1to2[9][10] = -0.801532846020733;
   fWeightMatrix1to2[10][10] = -1.54423125670701;
   fWeightMatrix1to2[0][11] = 0.662484960756071;
   fWeightMatrix1to2[1][11] = -0.525213886868657;
   fWeightMatrix1to2[2][11] = 0.231917188392508;
   fWeightMatrix1to2[3][11] = -1.33991818744167;
   fWeightMatrix1to2[4][11] = -0.945985499198927;
   fWeightMatrix1to2[5][11] = -1.45341888865879;
   fWeightMatrix1to2[6][11] = 0.765292018928697;
   fWeightMatrix1to2[7][11] = 0.77812517331726;
   fWeightMatrix1to2[8][11] = -0.390528983881897;
   fWeightMatrix1to2[9][11] = 0.665645310131135;
   fWeightMatrix1to2[10][11] = 0.699465166617412;
   fWeightMatrix1to2[0][12] = -0.319285106160488;
   fWeightMatrix1to2[1][12] = -0.264560935143222;
   fWeightMatrix1to2[2][12] = -0.700309173142946;
   fWeightMatrix1to2[3][12] = -0.591424974588088;
   fWeightMatrix1to2[4][12] = 1.53472666819057;
   fWeightMatrix1to2[5][12] = 1.03859033488307;
   fWeightMatrix1to2[6][12] = -2.28754807757538;
   fWeightMatrix1to2[7][12] = -2.23412176361639;
   fWeightMatrix1to2[8][12] = 0.172822374652678;
   fWeightMatrix1to2[9][12] = -0.243561177580136;
   fWeightMatrix1to2[10][12] = 0.500217589045797;
   // weight matrix from layer 2 to 3
   fWeightMatrix2to3[0][0] = -0.304380597562649;
   fWeightMatrix2to3[0][1] = -0.186821194346531;
   fWeightMatrix2to3[0][2] = -0.795371676144378;
   fWeightMatrix2to3[0][3] = 0.0457872109290413;
   fWeightMatrix2to3[0][4] = 0.626302241740498;
   fWeightMatrix2to3[0][5] = -1.01093345950281;
   fWeightMatrix2to3[0][6] = -1.19795363458502;
   fWeightMatrix2to3[0][7] = -0.295128108144209;
   fWeightMatrix2to3[0][8] = 0.959445856139188;
   fWeightMatrix2to3[0][9] = -0.243959132781375;
   fWeightMatrix2to3[0][10] = -0.881994132836739;
   fWeightMatrix2to3[0][11] = 0.694185925583831;
}

inline double ReadH6AONN5MEMLP::GetMvaValue__( const std::vector<double>& inputValues ) const
{
   if (inputValues.size() != (unsigned int)fLayerSize[0]-1) {
      std::cout << "Input vector needs to be of size " << fLayerSize[0]-1 << std::endl;
      return 0;
   }

   for (int l=0; l<fLayers; l++)
      for (int i=0; i<fLayerSize[l]; i++) fWeights[l][i]=0;

   for (int l=0; l<fLayers-1; l++)
      fWeights[l][fLayerSize[l]-1]=1;

   for (int i=0; i<fLayerSize[0]-1; i++)
      fWeights[0][i]=inputValues[i];

   // layer 0 to 1
   for (int o=0; o<fLayerSize[1]-1; o++) {
      for (int i=0; i<fLayerSize[0]; i++) {
         double inputVal = fWeightMatrix0to1[o][i] * fWeights[0][i];
         fWeights[1][o] += inputVal;
      }
      fWeights[1][o] = ActivationFnc(fWeights[1][o]);
   }
   // layer 1 to 2
   for (int o=0; o<fLayerSize[2]-1; o++) {
      for (int i=0; i<fLayerSize[1]; i++) {
         double inputVal = fWeightMatrix1to2[o][i] * fWeights[1][i];
         fWeights[2][o] += inputVal;
      }
      fWeights[2][o] = ActivationFnc(fWeights[2][o]);
   }
   // layer 2 to 3
   for (int o=0; o<fLayerSize[3]; o++) {
      for (int i=0; i<fLayerSize[2]; i++) {
         double inputVal = fWeightMatrix2to3[o][i] * fWeights[2][i];
         fWeights[3][o] += inputVal;
      }
   }

   return fWeights[3][0];
}

double ReadH6AONN5MEMLP::ActivationFnc(double x) const {
   // sigmoid
   return 1.0/(1.0+exp(-x));
}
   
// Clean up
inline void ReadH6AONN5MEMLP::Clear() 
{
   // nothing to clear
}