// 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 16:28:19 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: 21736


#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]
LRWg                          LRWg                              'F'    [0,0.999932587147]
LRWj                          LRWj                              'F'    [-0.00544115481898,1]
LRZZ                          LRZZ                              'F'    [0,1]
Met                           Met                               'F'    [15.0806331635,275.269592285]
MetDelPhi                     MetDelPhi                         'F'    [0.120642267168,3.12748098373]
MetSpec                       MetSpec                           'F'    [15.0024642944,178.184524536]
dPhiLeptons                   dPhiLeptons                       'F'    [0.00023341178894,3.14049983025]
dRLeptons                     dRLeptons                         'F'    [0.403980851173,4.5256857872]
dimass                        dimass                            'F'    [16.0008029938,557.91784668]


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

#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;
      fVmin[2] = 0;
      fVmax[2] = 0.999932587146759;
      fVmin[3] = -0.00544115481898189;
      fVmax[3] = 1;
      fVmin[4] = 0;
      fVmax[4] = 1;
      fVmin[5] = 15.0806331634521;
      fVmax[5] = 275.269592285156;
      fVmin[6] = 0.120642267167568;
      fVmax[6] = 3.12748098373413;
      fVmin[7] = 15.0024642944336;
      fVmax[7] = 178.184524536133;
      fVmin[8] = 0.00023341178894043;
      fVmax[8] = 3.14049983024597;
      fVmin[9] = 0.403980851173401;
      fVmax[9] = 4.52568578720093;
      fVmin[10] = 16.0008029937744;
      fVmax[10] = 557.917846679688;

      // 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] = 1.78587534612727;
   fWeightMatrix0to1[1][0] = 1.39808145070985;
   fWeightMatrix0to1[2][0] = -0.513179585912009;
   fWeightMatrix0to1[3][0] = 1.51208143475257;
   fWeightMatrix0to1[4][0] = 0.852583705928061;
   fWeightMatrix0to1[5][0] = 3.58016453718151;
   fWeightMatrix0to1[6][0] = 1.86807322679552;
   fWeightMatrix0to1[7][0] = -0.389771790886047;
   fWeightMatrix0to1[8][0] = 0.898411025311535;
   fWeightMatrix0to1[9][0] = 1.52615221570026;
   fWeightMatrix0to1[10][0] = 0.322598798463723;
   fWeightMatrix0to1[11][0] = 0.127620930661387;
   fWeightMatrix0to1[0][1] = 1.61856300064746;
   fWeightMatrix0to1[1][1] = 1.2508004137362;
   fWeightMatrix0to1[2][1] = 1.14555273475568;
   fWeightMatrix0to1[3][1] = -2.38685520498847;
   fWeightMatrix0to1[4][1] = 0.990120560587827;
   fWeightMatrix0to1[5][1] = 0.0582594506025728;
   fWeightMatrix0to1[6][1] = -1.67994005255503;
   fWeightMatrix0to1[7][1] = 1.57777338515478;
   fWeightMatrix0to1[8][1] = 2.47311490049152;
   fWeightMatrix0to1[9][1] = 1.26399627703814;
   fWeightMatrix0to1[10][1] = 0.546402453973295;
   fWeightMatrix0to1[11][1] = -0.795597747290522;
   fWeightMatrix0to1[0][2] = 0.560657199996271;
   fWeightMatrix0to1[1][2] = 0.220959366771511;
   fWeightMatrix0to1[2][2] = 0.00793419741458121;
   fWeightMatrix0to1[3][2] = -1.42763407243903;
   fWeightMatrix0to1[4][2] = 1.90474548272643;
   fWeightMatrix0to1[5][2] = 0.0110947021589814;
   fWeightMatrix0to1[6][2] = -0.0703674278991695;
   fWeightMatrix0to1[7][2] = -0.952902179241417;
   fWeightMatrix0to1[8][2] = -0.281751122975828;
   fWeightMatrix0to1[9][2] = -0.579020532914903;
   fWeightMatrix0to1[10][2] = -0.44121866023538;
   fWeightMatrix0to1[11][2] = 0.726954566976275;
   fWeightMatrix0to1[0][3] = -0.0781702638272787;
   fWeightMatrix0to1[1][3] = 0.562114095248046;
   fWeightMatrix0to1[2][3] = 1.29415904367419;
   fWeightMatrix0to1[3][3] = 1.40431433542528;
   fWeightMatrix0to1[4][3] = -0.918257353806234;
   fWeightMatrix0to1[5][3] = -0.334981201005296;
   fWeightMatrix0to1[6][3] = -0.726115191597661;
   fWeightMatrix0to1[7][3] = -1.62451910288858;
   fWeightMatrix0to1[8][3] = -0.505128752599966;
   fWeightMatrix0to1[9][3] = -1.28850615211903;
   fWeightMatrix0to1[10][3] = -0.0900617620202149;
   fWeightMatrix0to1[11][3] = 0.797913880774829;
   fWeightMatrix0to1[0][4] = 0.140304025790977;
   fWeightMatrix0to1[1][4] = 0.0501130209250728;
   fWeightMatrix0to1[2][4] = 1.34292032114309;
   fWeightMatrix0to1[3][4] = -1.0245532685625;
   fWeightMatrix0to1[4][4] = 0.0491787651146999;
   fWeightMatrix0to1[5][4] = -0.851862601083288;
   fWeightMatrix0to1[6][4] = -0.583816660592497;
   fWeightMatrix0to1[7][4] = 0.165750825797612;
   fWeightMatrix0to1[8][4] = -0.326577672160567;
   fWeightMatrix0to1[9][4] = 0.566084716959858;
   fWeightMatrix0to1[10][4] = -0.258322242810502;
   fWeightMatrix0to1[11][4] = -0.249932215644494;
   fWeightMatrix0to1[0][5] = -0.919309862678924;
   fWeightMatrix0to1[1][5] = -0.00733193235709649;
   fWeightMatrix0to1[2][5] = -1.65992430883959;
   fWeightMatrix0to1[3][5] = 0.391554090482956;
   fWeightMatrix0to1[4][5] = 1.02445360375544;
   fWeightMatrix0to1[5][5] = -1.69251980120263;
   fWeightMatrix0to1[6][5] = 1.85658327465462;
   fWeightMatrix0to1[7][5] = -0.535519946229393;
   fWeightMatrix0to1[8][5] = -0.254714473505672;
   fWeightMatrix0to1[9][5] = 0.545690135962659;
   fWeightMatrix0to1[10][5] = 0.384433903533899;
   fWeightMatrix0to1[11][5] = -1.05937703553016;
   fWeightMatrix0to1[0][6] = -1.03923798976492;
   fWeightMatrix0to1[1][6] = -1.15543851270292;
   fWeightMatrix0to1[2][6] = 1.01609050199625;
   fWeightMatrix0to1[3][6] = -0.832481000803386;
   fWeightMatrix0to1[4][6] = -0.0854564786520992;
   fWeightMatrix0to1[5][6] = -1.1830354136183;
   fWeightMatrix0to1[6][6] = -1.94087855410286;
   fWeightMatrix0to1[7][6] = 1.31281697005951;
   fWeightMatrix0to1[8][6] = 0.253422535589372;
   fWeightMatrix0to1[9][6] = 0.734511619609631;
   fWeightMatrix0to1[10][6] = 2.28400481988691;
   fWeightMatrix0to1[11][6] = 1.01609987470097;
   fWeightMatrix0to1[0][7] = -0.386018625385843;
   fWeightMatrix0to1[1][7] = 0.631857079168355;
   fWeightMatrix0to1[2][7] = 2.3335246906805;
   fWeightMatrix0to1[3][7] = -0.762181312909539;
   fWeightMatrix0to1[4][7] = 1.37753628973764;
   fWeightMatrix0to1[5][7] = -0.382022125376427;
   fWeightMatrix0to1[6][7] = -0.224536515622063;
   fWeightMatrix0to1[7][7] = -0.531158646382675;
   fWeightMatrix0to1[8][7] = 0.189572904496545;
   fWeightMatrix0to1[9][7] = 1.61993039856253;
   fWeightMatrix0to1[10][7] = -0.470629983218253;
   fWeightMatrix0to1[11][7] = 2.35309630899695;
   fWeightMatrix0to1[0][8] = -0.615413764907922;
   fWeightMatrix0to1[1][8] = -1.44533908014094;
   fWeightMatrix0to1[2][8] = 2.28539625722137;
   fWeightMatrix0to1[3][8] = -2.07463558144693;
   fWeightMatrix0to1[4][8] = 0.0668552595596359;
   fWeightMatrix0to1[5][8] = -0.232390485548503;
   fWeightMatrix0to1[6][8] = 0.116822018085899;
   fWeightMatrix0to1[7][8] = -0.220023192603143;
   fWeightMatrix0to1[8][8] = 1.92072918570465;
   fWeightMatrix0to1[9][8] = -0.890910384562118;
   fWeightMatrix0to1[10][8] = 1.01127565252843;
   fWeightMatrix0to1[11][8] = -1.20895128744163;
   fWeightMatrix0to1[0][9] = -0.473725172165015;
   fWeightMatrix0to1[1][9] = -1.91107762463087;
   fWeightMatrix0to1[2][9] = 1.9508689425643;
   fWeightMatrix0to1[3][9] = -1.20472049190951;
   fWeightMatrix0to1[4][9] = -0.299178271143344;
   fWeightMatrix0to1[5][9] = 0.191574911478058;
   fWeightMatrix0to1[6][9] = -1.04047105357132;
   fWeightMatrix0to1[7][9] = 0.917274884257074;
   fWeightMatrix0to1[8][9] = -1.17343539814481;
   fWeightMatrix0to1[9][9] = -2.07900089914366;
   fWeightMatrix0to1[10][9] = -2.32813346815752;
   fWeightMatrix0to1[11][9] = -0.0510817659041139;
   fWeightMatrix0to1[0][10] = -0.907250773369012;
   fWeightMatrix0to1[1][10] = 1.03489314876049;
   fWeightMatrix0to1[2][10] = 1.54923424230854;
   fWeightMatrix0to1[3][10] = -2.16349497442715;
   fWeightMatrix0to1[4][10] = 0.833086179383921;
   fWeightMatrix0to1[5][10] = -1.54394960967983;
   fWeightMatrix0to1[6][10] = -2.64614183107923;
   fWeightMatrix0to1[7][10] = 0.795304628602647;
   fWeightMatrix0to1[8][10] = -0.448364610399188;
   fWeightMatrix0to1[9][10] = -1.02978250736524;
   fWeightMatrix0to1[10][10] = -1.28196360338961;
   fWeightMatrix0to1[11][10] = -1.62943924681877;
   fWeightMatrix0to1[0][11] = -0.852252643139408;
   fWeightMatrix0to1[1][11] = -0.910045488488091;
   fWeightMatrix0to1[2][11] = -0.125972272991876;
   fWeightMatrix0to1[3][11] = 1.08824647278734;
   fWeightMatrix0to1[4][11] = 1.23116163383048;
   fWeightMatrix0to1[5][11] = 0.903224012560885;
   fWeightMatrix0to1[6][11] = -1.68357509248026;
   fWeightMatrix0to1[7][11] = -1.17178808336037;
   fWeightMatrix0to1[8][11] = 2.70979791194146;
   fWeightMatrix0to1[9][11] = -1.69153314488656;
   fWeightMatrix0to1[10][11] = 0.0393515173545834;
   fWeightMatrix0to1[11][11] = -0.243822819667016;
   // weight matrix from layer 1 to 2
   fWeightMatrix1to2[0][0] = -1.48026923851191;
   fWeightMatrix1to2[1][0] = -0.0529813420644063;
   fWeightMatrix1to2[2][0] = -0.943300338155797;
   fWeightMatrix1to2[3][0] = -0.796627211852415;
   fWeightMatrix1to2[4][0] = -2.0501407612521;
   fWeightMatrix1to2[5][0] = -0.207798734698458;
   fWeightMatrix1to2[6][0] = 1.61033349643164;
   fWeightMatrix1to2[7][0] = 1.34110048241957;
   fWeightMatrix1to2[8][0] = 1.45759366425646;
   fWeightMatrix1to2[9][0] = -2.69840357644617;
   fWeightMatrix1to2[10][0] = -0.660030086281013;
   fWeightMatrix1to2[0][1] = 0.849091626449971;
   fWeightMatrix1to2[1][1] = -1.6200058312565;
   fWeightMatrix1to2[2][1] = -0.995015031428817;
   fWeightMatrix1to2[3][1] = -0.0705320881541544;
   fWeightMatrix1to2[4][1] = 1.20748490197218;
   fWeightMatrix1to2[5][1] = -1.96902592663284;
   fWeightMatrix1to2[6][1] = -0.797408582652731;
   fWeightMatrix1to2[7][1] = -0.0093701446065152;
   fWeightMatrix1to2[8][1] = -1.41496412565125;
   fWeightMatrix1to2[9][1] = -1.57877322798366;
   fWeightMatrix1to2[10][1] = -0.248218081088283;
   fWeightMatrix1to2[0][2] = 0.549614170893893;
   fWeightMatrix1to2[1][2] = -0.268686155463622;
   fWeightMatrix1to2[2][2] = -1.60859816122785;
   fWeightMatrix1to2[3][2] = -0.20866214986771;
   fWeightMatrix1to2[4][2] = 1.43268513636993;
   fWeightMatrix1to2[5][2] = -0.933501161014245;
   fWeightMatrix1to2[6][2] = 0.893446649415195;
   fWeightMatrix1to2[7][2] = -2.07996145299459;
   fWeightMatrix1to2[8][2] = 0.387455340748484;
   fWeightMatrix1to2[9][2] = 0.0929876041234388;
   fWeightMatrix1to2[10][2] = -0.554585190889391;
   fWeightMatrix1to2[0][3] = -1.34809636919847;
   fWeightMatrix1to2[1][3] = -0.034265775111514;
   fWeightMatrix1to2[2][3] = 1.05458532289823;
   fWeightMatrix1to2[3][3] = -2.0543241753738;
   fWeightMatrix1to2[4][3] = 0.495673335453956;
   fWeightMatrix1to2[5][3] = -0.0657407558139899;
   fWeightMatrix1to2[6][3] = 1.26690693529904;
   fWeightMatrix1to2[7][3] = 0.0781644158500635;
   fWeightMatrix1to2[8][3] = -1.59460929823312;
   fWeightMatrix1to2[9][3] = -1.92717957764898;
   fWeightMatrix1to2[10][3] = -0.445402471283728;
   fWeightMatrix1to2[0][4] = 0.462919883497094;
   fWeightMatrix1to2[1][4] = 0.152810776001547;
   fWeightMatrix1to2[2][4] = 0.483912935295995;
   fWeightMatrix1to2[3][4] = -0.989908211759483;
   fWeightMatrix1to2[4][4] = 0.582540962275411;
   fWeightMatrix1to2[5][4] = 0.877778306343094;
   fWeightMatrix1to2[6][4] = -1.26169810077222;
   fWeightMatrix1to2[7][4] = -0.0545135222676675;
   fWeightMatrix1to2[8][4] = 0.848820137881586;
   fWeightMatrix1to2[9][4] = -0.138620197543513;
   fWeightMatrix1to2[10][4] = 0.112296278822955;
   fWeightMatrix1to2[0][5] = -0.498647951904513;
   fWeightMatrix1to2[1][5] = -0.0257218937422137;
   fWeightMatrix1to2[2][5] = -0.559753622920485;
   fWeightMatrix1to2[3][5] = -0.468688627169964;
   fWeightMatrix1to2[4][5] = -2.22051306476539;
   fWeightMatrix1to2[5][5] = -1.51592431523265;
   fWeightMatrix1to2[6][5] = -0.958561972129505;
   fWeightMatrix1to2[7][5] = 0.0830162284400266;
   fWeightMatrix1to2[8][5] = -2.24225987513636;
   fWeightMatrix1to2[9][5] = 1.67235177504493;
   fWeightMatrix1to2[10][5] = -0.871511968024477;
   fWeightMatrix1to2[0][6] = -1.25460203276195;
   fWeightMatrix1to2[1][6] = 0.975068264252646;
   fWeightMatrix1to2[2][6] = -1.24903629478271;
   fWeightMatrix1to2[3][6] = -1.88148350000168;
   fWeightMatrix1to2[4][6] = 0.689157916980315;
   fWeightMatrix1to2[5][6] = -1.52701382785529;
   fWeightMatrix1to2[6][6] = 0.317619545721224;
   fWeightMatrix1to2[7][6] = -2.6625109491886;
   fWeightMatrix1to2[8][6] = -1.08539330939571;
   fWeightMatrix1to2[9][6] = 0.959177358433797;
   fWeightMatrix1to2[10][6] = -2.99439722025558;
   fWeightMatrix1to2[0][7] = 1.09454927406465;
   fWeightMatrix1to2[1][7] = 0.18955193220264;
   fWeightMatrix1to2[2][7] = -1.19996612922173;
   fWeightMatrix1to2[3][7] = -1.15339771558486;
   fWeightMatrix1to2[4][7] = -1.27439268733743;
   fWeightMatrix1to2[5][7] = -0.137688848406843;
   fWeightMatrix1to2[6][7] = -0.76806148413452;
   fWeightMatrix1to2[7][7] = -2.02364203675715;
   fWeightMatrix1to2[8][7] = -0.0879662319974191;
   fWeightMatrix1to2[9][7] = -1.13775288027437;
   fWeightMatrix1to2[10][7] = 0.998469398041856;
   fWeightMatrix1to2[0][8] = -1.54109101840862;
   fWeightMatrix1to2[1][8] = -0.508984415664647;
   fWeightMatrix1to2[2][8] = 0.400582739352957;
   fWeightMatrix1to2[3][8] = 0.795745701566909;
   fWeightMatrix1to2[4][8] = -1.50437710176079;
   fWeightMatrix1to2[5][8] = 1.99711049557582;
   fWeightMatrix1to2[6][8] = -2.20585608471663;
   fWeightMatrix1to2[7][8] = -0.0896706657101816;
   fWeightMatrix1to2[8][8] = -0.523564200788631;
   fWeightMatrix1to2[9][8] = -2.38885280618939;
   fWeightMatrix1to2[10][8] = 1.21191030190497;
   fWeightMatrix1to2[0][9] = -0.308310305408622;
   fWeightMatrix1to2[1][9] = 1.04679600917199;
   fWeightMatrix1to2[2][9] = 1.40718191635588;
   fWeightMatrix1to2[3][9] = 0.113889631553552;
   fWeightMatrix1to2[4][9] = 0.956660537509395;
   fWeightMatrix1to2[5][9] = -0.886054403138063;
   fWeightMatrix1to2[6][9] = -1.3115949243087;
   fWeightMatrix1to2[7][9] = -0.611935635003494;
   fWeightMatrix1to2[8][9] = -0.708720173755782;
   fWeightMatrix1to2[9][9] = -1.33232664693101;
   fWeightMatrix1to2[10][9] = -0.847441703703753;
   fWeightMatrix1to2[0][10] = 0.898271163901063;
   fWeightMatrix1to2[1][10] = -0.920411560706986;
   fWeightMatrix1to2[2][10] = -2.02082538524965;
   fWeightMatrix1to2[3][10] = 1.44984400636241;
   fWeightMatrix1to2[4][10] = -1.56425523958852;
   fWeightMatrix1to2[5][10] = -0.811266870714434;
   fWeightMatrix1to2[6][10] = -1.42802833150812;
   fWeightMatrix1to2[7][10] = 0.1706406075782;
   fWeightMatrix1to2[8][10] = -0.405208407769471;
   fWeightMatrix1to2[9][10] = -0.346776591540579;
   fWeightMatrix1to2[10][10] = -1.13618370316389;
   fWeightMatrix1to2[0][11] = 0.705158127683871;
   fWeightMatrix1to2[1][11] = -0.718228474205091;
   fWeightMatrix1to2[2][11] = 0.572858698481044;
   fWeightMatrix1to2[3][11] = -1.20573270084937;
   fWeightMatrix1to2[4][11] = -0.730375891455865;
   fWeightMatrix1to2[5][11] = -1.14523010147381;
   fWeightMatrix1to2[6][11] = 0.993727397564879;
   fWeightMatrix1to2[7][11] = 0.899136435062973;
   fWeightMatrix1to2[8][11] = -0.307030050489899;
   fWeightMatrix1to2[9][11] = 1.19597724649522;
   fWeightMatrix1to2[10][11] = 0.593180252471612;
   fWeightMatrix1to2[0][12] = -0.136776830603561;
   fWeightMatrix1to2[1][12] = -0.320854487333603;
   fWeightMatrix1to2[2][12] = -0.723623926400946;
   fWeightMatrix1to2[3][12] = -0.408491576026416;
   fWeightMatrix1to2[4][12] = 1.50427613404371;
   fWeightMatrix1to2[5][12] = 1.77928847139841;
   fWeightMatrix1to2[6][12] = -2.03511534846127;
   fWeightMatrix1to2[7][12] = -2.28394105046309;
   fWeightMatrix1to2[8][12] = 0.102313905802244;
   fWeightMatrix1to2[9][12] = -0.173623877480985;
   fWeightMatrix1to2[10][12] = 1.28823378545119;
   // weight matrix from layer 2 to 3
   fWeightMatrix2to3[0][0] = -0.0541489931692151;
   fWeightMatrix2to3[0][1] = -0.187997845817641;
   fWeightMatrix2to3[0][2] = -1.1600337343807;
   fWeightMatrix2to3[0][3] = -0.436593475003022;
   fWeightMatrix2to3[0][4] = 0.03912419657247;
   fWeightMatrix2to3[0][5] = -0.71507457235993;
   fWeightMatrix2to3[0][6] = -1.44341444221455;
   fWeightMatrix2to3[0][7] = 0.0144030382603487;
   fWeightMatrix2to3[0][8] = 0.679143763588042;
   fWeightMatrix2to3[0][9] = 1.18425831428716;
   fWeightMatrix2to3[0][10] = -0.437568804092269;
   fWeightMatrix2to3[0][11] = 1.01477392138237;
}

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
}