// 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 16:28:17 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: 21776


#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'    [0,1.001734972]
LRWg                          LRWg                              'F'    [0,0.999911367893]
LRWj                          LRWj                              'F'    [-0.0757067129016,1]
LRZZ                          LRZZ                              'F'    [0,1]
Met                           Met                               'F'    [15.0942249298,324.415008545]
MetDelPhi                     MetDelPhi                         'F'    [0.118904195726,3.13655138016]
MetSpec                       MetSpec                           'F'    [15.0046358109,192.753829956]
dPhiLeptons                   dPhiLeptons                       'F'    [0.000216960906982,3.14020013809]
dRLeptons                     dRLeptons                         'F'    [0.401400476694,4.23354482651]
dimass                        dimass                            'F'    [16.0013523102,531.617553711]


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

#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] = 1.00173497200012;
      fVmin[2] = 0;
      fVmax[2] = 0.999911367893219;
      fVmin[3] = -0.0757067129015923;
      fVmax[3] = 1;
      fVmin[4] = 0;
      fVmax[4] = 1;
      fVmin[5] = 15.0942249298096;
      fVmax[5] = 324.415008544922;
      fVmin[6] = 0.118904195725918;
      fVmax[6] = 3.13655138015747;
      fVmin[7] = 15.0046358108521;
      fVmax[7] = 192.753829956055;
      fVmin[8] = 0.000216960906982422;
      fVmax[8] = 3.14020013809204;
      fVmin[9] = 0.401400476694107;
      fVmax[9] = 4.23354482650757;
      fVmin[10] = 16.0013523101807;
      fVmax[10] = 531.617553710938;

      // 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] = 2.37342813496263;
   fWeightMatrix0to1[1][0] = 3.58993918085292;
   fWeightMatrix0to1[2][0] = 0.338664205692022;
   fWeightMatrix0to1[3][0] = 1.5894497319466;
   fWeightMatrix0to1[4][0] = 0.668360583702111;
   fWeightMatrix0to1[5][0] = 2.74446200956365;
   fWeightMatrix0to1[6][0] = 1.64177651342004;
   fWeightMatrix0to1[7][0] = 0.53382632371225;
   fWeightMatrix0to1[8][0] = 0.729933862909135;
   fWeightMatrix0to1[9][0] = 1.28430429627484;
   fWeightMatrix0to1[10][0] = 0.249260878375066;
   fWeightMatrix0to1[11][0] = 0.658386129428282;
   fWeightMatrix0to1[0][1] = 1.4535247447796;
   fWeightMatrix0to1[1][1] = 0.955612797752677;
   fWeightMatrix0to1[2][1] = 1.26845267706466;
   fWeightMatrix0to1[3][1] = -1.54474278034346;
   fWeightMatrix0to1[4][1] = 0.999522415356529;
   fWeightMatrix0to1[5][1] = 0.473613229718409;
   fWeightMatrix0to1[6][1] = -1.05181181085893;
   fWeightMatrix0to1[7][1] = 1.58832128687388;
   fWeightMatrix0to1[8][1] = 1.91383606001448;
   fWeightMatrix0to1[9][1] = 0.491696548463063;
   fWeightMatrix0to1[10][1] = 0.368673066186752;
   fWeightMatrix0to1[11][1] = -0.117089588459658;
   fWeightMatrix0to1[0][2] = 0.14279247667158;
   fWeightMatrix0to1[1][2] = 1.20816822611078;
   fWeightMatrix0to1[2][2] = 0.0435613786836967;
   fWeightMatrix0to1[3][2] = -1.92487236881959;
   fWeightMatrix0to1[4][2] = 2.57037735145034;
   fWeightMatrix0to1[5][2] = 0.000181045571687351;
   fWeightMatrix0to1[6][2] = 0.0728604367474736;
   fWeightMatrix0to1[7][2] = -0.679800570123907;
   fWeightMatrix0to1[8][2] = -0.271024159270371;
   fWeightMatrix0to1[9][2] = -0.794952409622495;
   fWeightMatrix0to1[10][2] = -0.806341721218475;
   fWeightMatrix0to1[11][2] = 0.321036613101015;
   fWeightMatrix0to1[0][3] = 0.634282748420431;
   fWeightMatrix0to1[1][3] = 0.626717832356846;
   fWeightMatrix0to1[2][3] = 1.03515176868901;
   fWeightMatrix0to1[3][3] = 1.52404995400191;
   fWeightMatrix0to1[4][3] = -0.878561356591494;
   fWeightMatrix0to1[5][3] = -0.249710941056184;
   fWeightMatrix0to1[6][3] = -0.677749320752645;
   fWeightMatrix0to1[7][3] = -1.86255513288927;
   fWeightMatrix0to1[8][3] = -0.80080942251502;
   fWeightMatrix0to1[9][3] = -1.24658164734053;
   fWeightMatrix0to1[10][3] = -1.00288419760382;
   fWeightMatrix0to1[11][3] = 0.433838395214099;
   fWeightMatrix0to1[0][4] = 0.572030859317365;
   fWeightMatrix0to1[1][4] = -0.33090266688426;
   fWeightMatrix0to1[2][4] = 1.6110714559879;
   fWeightMatrix0to1[3][4] = -1.13374833578558;
   fWeightMatrix0to1[4][4] = 0.606742894253393;
   fWeightMatrix0to1[5][4] = -0.825578387733247;
   fWeightMatrix0to1[6][4] = -0.878062358721886;
   fWeightMatrix0to1[7][4] = 0.237231393325083;
   fWeightMatrix0to1[8][4] = -0.25109895723629;
   fWeightMatrix0to1[9][4] = 0.852132197651493;
   fWeightMatrix0to1[10][4] = -0.111701965898716;
   fWeightMatrix0to1[11][4] = -0.480683603108649;
   fWeightMatrix0to1[0][5] = -0.789209059874959;
   fWeightMatrix0to1[1][5] = -0.00384461962492863;
   fWeightMatrix0to1[2][5] = -2.36881688491174;
   fWeightMatrix0to1[3][5] = 0.845766256584591;
   fWeightMatrix0to1[4][5] = 0.933251017479739;
   fWeightMatrix0to1[5][5] = -1.71930820959073;
   fWeightMatrix0to1[6][5] = 1.27013692722248;
   fWeightMatrix0to1[7][5] = -0.682692315979242;
   fWeightMatrix0to1[8][5] = -0.239250233913297;
   fWeightMatrix0to1[9][5] = 1.17438369831945;
   fWeightMatrix0to1[10][5] = -0.272908144086502;
   fWeightMatrix0to1[11][5] = -0.830760058457481;
   fWeightMatrix0to1[0][6] = -0.403690871406826;
   fWeightMatrix0to1[1][6] = -0.110025802776709;
   fWeightMatrix0to1[2][6] = 1.47577470024046;
   fWeightMatrix0to1[3][6] = -0.649737859328097;
   fWeightMatrix0to1[4][6] = 0.676288464602928;
   fWeightMatrix0to1[5][6] = -0.59737116919764;
   fWeightMatrix0to1[6][6] = -1.56738454381102;
   fWeightMatrix0to1[7][6] = 1.26937277056895;
   fWeightMatrix0to1[8][6] = 0.329380779118393;
   fWeightMatrix0to1[9][6] = 0.697537532351828;
   fWeightMatrix0to1[10][6] = 2.15369960740655;
   fWeightMatrix0to1[11][6] = 0.895331700889566;
   fWeightMatrix0to1[0][7] = -0.057832595072384;
   fWeightMatrix0to1[1][7] = 0.539522987390425;
   fWeightMatrix0to1[2][7] = 1.44512679898939;
   fWeightMatrix0to1[3][7] = -0.236980033882674;
   fWeightMatrix0to1[4][7] = 1.14485177351153;
   fWeightMatrix0to1[5][7] = 0.113295761308753;
   fWeightMatrix0to1[6][7] = -0.232461483934473;
   fWeightMatrix0to1[7][7] = -0.920850220473219;
   fWeightMatrix0to1[8][7] = -0.330506239719541;
   fWeightMatrix0to1[9][7] = 2.39304332911694;
   fWeightMatrix0to1[10][7] = -1.1730846660626;
   fWeightMatrix0to1[11][7] = 2.29177963289619;
   fWeightMatrix0to1[0][8] = -0.137505838697257;
   fWeightMatrix0to1[1][8] = 0.445315803707747;
   fWeightMatrix0to1[2][8] = 2.54338131234168;
   fWeightMatrix0to1[3][8] = -2.43635367623589;
   fWeightMatrix0to1[4][8] = 0.0642346059748409;
   fWeightMatrix0to1[5][8] = 0.571479789301522;
   fWeightMatrix0to1[6][8] = -0.0762305169308716;
   fWeightMatrix0to1[7][8] = -0.875696633491537;
   fWeightMatrix0to1[8][8] = 1.8555665654387;
   fWeightMatrix0to1[9][8] = 0.357099891657498;
   fWeightMatrix0to1[10][8] = 0.706528539806963;
   fWeightMatrix0to1[11][8] = -1.58443149108788;
   fWeightMatrix0to1[0][9] = 0.0809955553940687;
   fWeightMatrix0to1[1][9] = -1.41589913331379;
   fWeightMatrix0to1[2][9] = 1.78725132640883;
   fWeightMatrix0to1[3][9] = -1.58759114316406;
   fWeightMatrix0to1[4][9] = -0.345193061025767;
   fWeightMatrix0to1[5][9] = 0.540727299720033;
   fWeightMatrix0to1[6][9] = -1.51487012740436;
   fWeightMatrix0to1[7][9] = 0.633381274725067;
   fWeightMatrix0to1[8][9] = -1.28797628807151;
   fWeightMatrix0to1[9][9] = -1.67604811955909;
   fWeightMatrix0to1[10][9] = -1.19750449797741;
   fWeightMatrix0to1[11][9] = -0.984659159587844;
   fWeightMatrix0to1[0][10] = -0.476600181041174;
   fWeightMatrix0to1[1][10] = 1.88356660744512;
   fWeightMatrix0to1[2][10] = 1.44650848846528;
   fWeightMatrix0to1[3][10] = -1.82486303993091;
   fWeightMatrix0to1[4][10] = 0.709998207620988;
   fWeightMatrix0to1[5][10] = -1.37942519729816;
   fWeightMatrix0to1[6][10] = -1.9345598445008;
   fWeightMatrix0to1[7][10] = 0.774129767115561;
   fWeightMatrix0to1[8][10] = -0.499314372797675;
   fWeightMatrix0to1[9][10] = -0.21242119877639;
   fWeightMatrix0to1[10][10] = -1.29931506922598;
   fWeightMatrix0to1[11][10] = -1.58849718066343;
   fWeightMatrix0to1[0][11] = -1.29128858697511;
   fWeightMatrix0to1[1][11] = -1.49869133411648;
   fWeightMatrix0to1[2][11] = -0.0639760120993544;
   fWeightMatrix0to1[3][11] = 1.05464683628148;
   fWeightMatrix0to1[4][11] = 1.36872590722294;
   fWeightMatrix0to1[5][11] = 1.17361601767406;
   fWeightMatrix0to1[6][11] = -0.967745962643704;
   fWeightMatrix0to1[7][11] = -1.31384768686912;
   fWeightMatrix0to1[8][11] = 2.52225548022997;
   fWeightMatrix0to1[9][11] = -2.35357757019181;
   fWeightMatrix0to1[10][11] = 0.299878667986015;
   fWeightMatrix0to1[11][11] = -0.503252511646577;
   // weight matrix from layer 1 to 2
   fWeightMatrix1to2[0][0] = -1.51623806756891;
   fWeightMatrix1to2[1][0] = 0.184827950699611;
   fWeightMatrix1to2[2][0] = -0.739662578296967;
   fWeightMatrix1to2[3][0] = -0.991772198084169;
   fWeightMatrix1to2[4][0] = -2.08776246136573;
   fWeightMatrix1to2[5][0] = 1.17493660850959;
   fWeightMatrix1to2[6][0] = 1.62607131694562;
   fWeightMatrix1to2[7][0] = 1.28733009874815;
   fWeightMatrix1to2[8][0] = 1.59374401250413;
   fWeightMatrix1to2[9][0] = -2.05212442909586;
   fWeightMatrix1to2[10][0] = 0.0889102917508986;
   fWeightMatrix1to2[0][1] = 0.982862219433751;
   fWeightMatrix1to2[1][1] = -1.54618326495054;
   fWeightMatrix1to2[2][1] = -0.960900002525102;
   fWeightMatrix1to2[3][1] = -0.0740076871864858;
   fWeightMatrix1to2[4][1] = 1.16607283982194;
   fWeightMatrix1to2[5][1] = -2.80222872980793;
   fWeightMatrix1to2[6][1] = -0.811421778399519;
   fWeightMatrix1to2[7][1] = -0.189692953877165;
   fWeightMatrix1to2[8][1] = -1.3878508749117;
   fWeightMatrix1to2[9][1] = -1.45748358167352;
   fWeightMatrix1to2[10][1] = 0.120387160317765;
   fWeightMatrix1to2[0][2] = 0.55199078980152;
   fWeightMatrix1to2[1][2] = -0.231942956688617;
   fWeightMatrix1to2[2][2] = -1.66051995910664;
   fWeightMatrix1to2[3][2] = -0.428763044980828;
   fWeightMatrix1to2[4][2] = 1.51284765574483;
   fWeightMatrix1to2[5][2] = -0.415472717080269;
   fWeightMatrix1to2[6][2] = 0.870408046251903;
   fWeightMatrix1to2[7][2] = -2.33301081911643;
   fWeightMatrix1to2[8][2] = 0.359612918728997;
   fWeightMatrix1to2[9][2] = 0.0934837796269547;
   fWeightMatrix1to2[10][2] = -0.820930786373556;
   fWeightMatrix1to2[0][3] = -1.34361963783484;
   fWeightMatrix1to2[1][3] = 0.118480035898314;
   fWeightMatrix1to2[2][3] = 1.11258806954146;
   fWeightMatrix1to2[3][3] = -2.01729743801878;
   fWeightMatrix1to2[4][3] = 0.550166679178709;
   fWeightMatrix1to2[5][3] = -0.29666004905899;
   fWeightMatrix1to2[6][3] = 1.17574599913594;
   fWeightMatrix1to2[7][3] = 0.272622751622419;
   fWeightMatrix1to2[8][3] = -1.65049179047423;
   fWeightMatrix1to2[9][3] = -2.0222419718269;
   fWeightMatrix1to2[10][3] = -0.58273252888926;
   fWeightMatrix1to2[0][4] = 0.426872327625924;
   fWeightMatrix1to2[1][4] = 0.0680136032799156;
   fWeightMatrix1to2[2][4] = 0.533118303956917;
   fWeightMatrix1to2[3][4] = -1.02162053598183;
   fWeightMatrix1to2[4][4] = 0.307347708334249;
   fWeightMatrix1to2[5][4] = 1.97609839795398;
   fWeightMatrix1to2[6][4] = -1.34626907411128;
   fWeightMatrix1to2[7][4] = 0.316316296687998;
   fWeightMatrix1to2[8][4] = 0.708298447933848;
   fWeightMatrix1to2[9][4] = 0.0962865161583868;
   fWeightMatrix1to2[10][4] = -0.35815587308585;
   fWeightMatrix1to2[0][5] = -0.589508269953756;
   fWeightMatrix1to2[1][5] = -0.0215864733513187;
   fWeightMatrix1to2[2][5] = -0.629755476313241;
   fWeightMatrix1to2[3][5] = -0.613060308596014;
   fWeightMatrix1to2[4][5] = -2.15589983405348;
   fWeightMatrix1to2[5][5] = -0.827136920615695;
   fWeightMatrix1to2[6][5] = -0.951808182130076;
   fWeightMatrix1to2[7][5] = 0.207929726441392;
   fWeightMatrix1to2[8][5] = -2.1214871690763;
   fWeightMatrix1to2[9][5] = 1.68060407924898;
   fWeightMatrix1to2[10][5] = -0.879562272263614;
   fWeightMatrix1to2[0][6] = -1.03725079963359;
   fWeightMatrix1to2[1][6] = 0.970352367615285;
   fWeightMatrix1to2[2][6] = -1.16104399522579;
   fWeightMatrix1to2[3][6] = -1.96422353013351;
   fWeightMatrix1to2[4][6] = 0.650940360905191;
   fWeightMatrix1to2[5][6] = -1.85927423266037;
   fWeightMatrix1to2[6][6] = 0.437792155920744;
   fWeightMatrix1to2[7][6] = -2.66323336249917;
   fWeightMatrix1to2[8][6] = -0.99805863823304;
   fWeightMatrix1to2[9][6] = 0.772959083260401;
   fWeightMatrix1to2[10][6] = -3.12178061948167;
   fWeightMatrix1to2[0][7] = 1.11018236782103;
   fWeightMatrix1to2[1][7] = 0.150169655820026;
   fWeightMatrix1to2[2][7] = -1.11994436469963;
   fWeightMatrix1to2[3][7] = -1.35181482549632;
   fWeightMatrix1to2[4][7] = -1.36290910770776;
   fWeightMatrix1to2[5][7] = -0.24225165754938;
   fWeightMatrix1to2[6][7] = -0.66306921723194;
   fWeightMatrix1to2[7][7] = -1.81134770945556;
   fWeightMatrix1to2[8][7] = -0.0671893504544516;
   fWeightMatrix1to2[9][7] = -1.0528538541127;
   fWeightMatrix1to2[10][7] = 1.22259755277792;
   fWeightMatrix1to2[0][8] = -1.65982170511128;
   fWeightMatrix1to2[1][8] = -0.462625300471405;
   fWeightMatrix1to2[2][8] = 0.80199120448955;
   fWeightMatrix1to2[3][8] = 0.73296759293051;
   fWeightMatrix1to2[4][8] = -1.45953540524464;
   fWeightMatrix1to2[5][8] = 2.23840952910728;
   fWeightMatrix1to2[6][8] = -2.31270617057378;
   fWeightMatrix1to2[7][8] = 0.457452792139321;
   fWeightMatrix1to2[8][8] = -0.673148254416909;
   fWeightMatrix1to2[9][8] = -1.85203869473412;
   fWeightMatrix1to2[10][8] = 0.788119383818947;
   fWeightMatrix1to2[0][9] = -0.226969155275253;
   fWeightMatrix1to2[1][9] = 1.21090272563256;
   fWeightMatrix1to2[2][9] = 1.29586074326756;
   fWeightMatrix1to2[3][9] = 0.0983214237234235;
   fWeightMatrix1to2[4][9] = 0.866245236015715;
   fWeightMatrix1to2[5][9] = -1.43412875531251;
   fWeightMatrix1to2[6][9] = -1.19677515635306;
   fWeightMatrix1to2[7][9] = -0.641892810826205;
   fWeightMatrix1to2[8][9] = -0.53462618540411;
   fWeightMatrix1to2[9][9] = -1.28944776722575;
   fWeightMatrix1to2[10][9] = -0.691542083006963;
   fWeightMatrix1to2[0][10] = 0.729241595351513;
   fWeightMatrix1to2[1][10] = -0.932794828904791;
   fWeightMatrix1to2[2][10] = -2.12734274961761;
   fWeightMatrix1to2[3][10] = 1.45080319533799;
   fWeightMatrix1to2[4][10] = -1.50713053655621;
   fWeightMatrix1to2[5][10] = -0.768887032596649;
   fWeightMatrix1to2[6][10] = -1.35039608494726;
   fWeightMatrix1to2[7][10] = 0.473874968798669;
   fWeightMatrix1to2[8][10] = -0.379285826337384;
   fWeightMatrix1to2[9][10] = -0.576582087022701;
   fWeightMatrix1to2[10][10] = -0.941092376715386;
   fWeightMatrix1to2[0][11] = 0.824442863477308;
   fWeightMatrix1to2[1][11] = -0.649459754462398;
   fWeightMatrix1to2[2][11] = 0.106005521107572;
   fWeightMatrix1to2[3][11] = -1.24667287880825;
   fWeightMatrix1to2[4][11] = -0.805899139712339;
   fWeightMatrix1to2[5][11] = -2.00174678870456;
   fWeightMatrix1to2[6][11] = 0.772449704534127;
   fWeightMatrix1to2[7][11] = 0.884557295466503;
   fWeightMatrix1to2[8][11] = -0.422005679078032;
   fWeightMatrix1to2[9][11] = 0.840330760423436;
   fWeightMatrix1to2[10][11] = 0.494024920312217;
   fWeightMatrix1to2[0][12] = -0.209767300746941;
   fWeightMatrix1to2[1][12] = -0.206192068102747;
   fWeightMatrix1to2[2][12] = -0.662063839275546;
   fWeightMatrix1to2[3][12] = -0.436615019269631;
   fWeightMatrix1to2[4][12] = 1.54664746015801;
   fWeightMatrix1to2[5][12] = 1.67472673084579;
   fWeightMatrix1to2[6][12] = -2.16136160611941;
   fWeightMatrix1to2[7][12] = -1.99356020503007;
   fWeightMatrix1to2[8][12] = 0.019303486004646;
   fWeightMatrix1to2[9][12] = -0.149977793234266;
   fWeightMatrix1to2[10][12] = 0.570472802725687;
   // weight matrix from layer 2 to 3
   fWeightMatrix2to3[0][0] = 0.393774631577515;
   fWeightMatrix2to3[0][1] = -0.192762564581658;
   fWeightMatrix2to3[0][2] = -1.23847719644697;
   fWeightMatrix2to3[0][3] = -0.663362130846739;
   fWeightMatrix2to3[0][4] = 0.107918263496116;
   fWeightMatrix2to3[0][5] = -0.927010140935173;
   fWeightMatrix2to3[0][6] = -1.33472750471752;
   fWeightMatrix2to3[0][7] = -0.784439077770128;
   fWeightMatrix2to3[0][8] = 0.529613750210866;
   fWeightMatrix2to3[0][9] = 0.554857120531663;
   fWeightMatrix2to3[0][10] = -0.682076672947492;
   fWeightMatrix2to3[0][11] = 1.15788311617804;
}

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
}