// 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 16:21:51 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: 18312


#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'    [0,0.999921858311]
LRWW                          LRWW                              'F'    [0,1]
LRWg                          LRWg                              'F'    [0,0.999933362007]
LRWj                          LRWj                              'F'    [0,1]
LRZZ                          LRZZ                              'F'    [0,1]
Met                           Met                               'F'    [15.0806331635,233.529418945]
MetDelPhi                     MetDelPhi                         'F'    [0.118904195726,3.13627409935]
MetSpec                       MetSpec                           'F'    [15.0246295929,171.627700806]
dPhiLeptons                   dPhiLeptons                       'F'    [9.91821289062e-05,3.1400179863]
dRLeptons                     dRLeptons                         'F'    [0.400271952152,4.6129732132]
dimass                        dimass                            'F'    [16.0121879578,578.400939941]


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

#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] = 0.999921858310699;
      fVmin[1] = 0;
      fVmax[1] = 1;
      fVmin[2] = 0;
      fVmax[2] = 0.999933362007141;
      fVmin[3] = 0;
      fVmax[3] = 1;
      fVmin[4] = 0;
      fVmax[4] = 1;
      fVmin[5] = 15.0806331634521;
      fVmax[5] = 233.529418945312;
      fVmin[6] = 0.118904195725918;
      fVmax[6] = 3.13627409934998;
      fVmin[7] = 15.0246295928955;
      fVmax[7] = 171.627700805664;
      fVmin[8] = 9.918212890625e-05;
      fVmax[8] = 3.14001798629761;
      fVmin[9] = 0.400271952152252;
      fVmax[9] = 4.6129732131958;
      fVmin[10] = 16.0121879577637;
      fVmax[10] = 578.400939941406;

      // 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] = 1.49882997664669;
   fWeightMatrix0to1[1][0] = 1.50273710141075;
   fWeightMatrix0to1[2][0] = -0.566712404807425;
   fWeightMatrix0to1[3][0] = 1.85559039923621;
   fWeightMatrix0to1[4][0] = 0.0285150841052317;
   fWeightMatrix0to1[5][0] = 3.55631158623919;
   fWeightMatrix0to1[6][0] = 1.44337981189335;
   fWeightMatrix0to1[7][0] = -0.846735229018476;
   fWeightMatrix0to1[8][0] = 0.295843178716473;
   fWeightMatrix0to1[9][0] = 1.66171683223033;
   fWeightMatrix0to1[10][0] = 0.693211283355864;
   fWeightMatrix0to1[11][0] = 0.280073695424815;
   fWeightMatrix0to1[0][1] = 1.28337542703234;
   fWeightMatrix0to1[1][1] = 1.54308249680581;
   fWeightMatrix0to1[2][1] = 1.20138240261653;
   fWeightMatrix0to1[3][1] = -2.05786930473246;
   fWeightMatrix0to1[4][1] = 1.26554175304051;
   fWeightMatrix0to1[5][1] = -0.436480487648247;
   fWeightMatrix0to1[6][1] = -1.52659980348027;
   fWeightMatrix0to1[7][1] = 1.60300020057399;
   fWeightMatrix0to1[8][1] = 2.25617307372046;
   fWeightMatrix0to1[9][1] = 1.41463401702772;
   fWeightMatrix0to1[10][1] = 1.08054149678757;
   fWeightMatrix0to1[11][1] = -0.336655626386065;
   fWeightMatrix0to1[0][2] = 0.725860867242902;
   fWeightMatrix0to1[1][2] = 0.938223072559066;
   fWeightMatrix0to1[2][2] = -0.10523811279057;
   fWeightMatrix0to1[3][2] = -1.40017003757819;
   fWeightMatrix0to1[4][2] = 2.09986915537873;
   fWeightMatrix0to1[5][2] = -0.440553870221425;
   fWeightMatrix0to1[6][2] = -0.257413744216161;
   fWeightMatrix0to1[7][2] = -0.986783795507718;
   fWeightMatrix0to1[8][2] = -0.568461995154445;
   fWeightMatrix0to1[9][2] = -0.595557185286166;
   fWeightMatrix0to1[10][2] = -1.01435534446386;
   fWeightMatrix0to1[11][2] = 0.485663505944747;
   fWeightMatrix0to1[0][3] = 0.268991965444482;
   fWeightMatrix0to1[1][3] = 0.571588809363051;
   fWeightMatrix0to1[2][3] = 1.26914028150529;
   fWeightMatrix0to1[3][3] = 1.26002456986963;
   fWeightMatrix0to1[4][3] = -1.46006270696601;
   fWeightMatrix0to1[5][3] = 0.113058657332768;
   fWeightMatrix0to1[6][3] = -0.988145417834562;
   fWeightMatrix0to1[7][3] = -1.4527662255869;
   fWeightMatrix0to1[8][3] = 0.017154334087645;
   fWeightMatrix0to1[9][3] = -1.81848464917984;
   fWeightMatrix0to1[10][3] = -0.759416096782015;
   fWeightMatrix0to1[11][3] = 0.852685587997105;
   fWeightMatrix0to1[0][4] = 0.378095033735342;
   fWeightMatrix0to1[1][4] = -0.366026719852706;
   fWeightMatrix0to1[2][4] = 1.21538005384837;
   fWeightMatrix0to1[3][4] = -1.21091340603423;
   fWeightMatrix0to1[4][4] = 0.0989574845296566;
   fWeightMatrix0to1[5][4] = -0.832023144301221;
   fWeightMatrix0to1[6][4] = -0.875283742899635;
   fWeightMatrix0to1[7][4] = 0.000455309443619238;
   fWeightMatrix0to1[8][4] = -0.254726956891825;
   fWeightMatrix0to1[9][4] = 0.750966957604668;
   fWeightMatrix0to1[10][4] = 0.0881784797097952;
   fWeightMatrix0to1[11][4] = -0.140724949433035;
   fWeightMatrix0to1[0][5] = -1.04659224569258;
   fWeightMatrix0to1[1][5] = -0.604407238741956;
   fWeightMatrix0to1[2][5] = -1.90244159426466;
   fWeightMatrix0to1[3][5] = 0.00390185624476204;
   fWeightMatrix0to1[4][5] = 1.12415138836943;
   fWeightMatrix0to1[5][5] = -1.96621470381464;
   fWeightMatrix0to1[6][5] = 0.724670559868719;
   fWeightMatrix0to1[7][5] = -0.873736376056419;
   fWeightMatrix0to1[8][5] = -0.245496883481544;
   fWeightMatrix0to1[9][5] = 0.261308255544317;
   fWeightMatrix0to1[10][5] = 0.199167721647133;
   fWeightMatrix0to1[11][5] = -0.717684723943563;
   fWeightMatrix0to1[0][6] = -0.991635178578782;
   fWeightMatrix0to1[1][6] = -0.623209113168749;
   fWeightMatrix0to1[2][6] = 1.096792812569;
   fWeightMatrix0to1[3][6] = -0.633195215779744;
   fWeightMatrix0to1[4][6] = -0.305402337242563;
   fWeightMatrix0to1[5][6] = -0.58488825021215;
   fWeightMatrix0to1[6][6] = -2.35932966546663;
   fWeightMatrix0to1[7][6] = 1.82540398710115;
   fWeightMatrix0to1[8][6] = -0.237142013182783;
   fWeightMatrix0to1[9][6] = 0.686649025062828;
   fWeightMatrix0to1[10][6] = 1.59430028579304;
   fWeightMatrix0to1[11][6] = 0.901183405273222;
   fWeightMatrix0to1[0][7] = -0.710720590765317;
   fWeightMatrix0to1[1][7] = 0.213880226582643;
   fWeightMatrix0to1[2][7] = 1.99045931283655;
   fWeightMatrix0to1[3][7] = -1.17686636602443;
   fWeightMatrix0to1[4][7] = 1.38676745508859;
   fWeightMatrix0to1[5][7] = -0.315236777835268;
   fWeightMatrix0to1[6][7] = -0.591385433484942;
   fWeightMatrix0to1[7][7] = -0.75708838101247;
   fWeightMatrix0to1[8][7] = -0.36155327101873;
   fWeightMatrix0to1[9][7] = 1.53966147699526;
   fWeightMatrix0to1[10][7] = -0.971059663087132;
   fWeightMatrix0to1[11][7] = 2.82900252711097;
   fWeightMatrix0to1[0][8] = -1.07049816490453;
   fWeightMatrix0to1[1][8] = -0.780581667078818;
   fWeightMatrix0to1[2][8] = 1.86187482799198;
   fWeightMatrix0to1[3][8] = -2.07794489327706;
   fWeightMatrix0to1[4][8] = -0.246069302374294;
   fWeightMatrix0to1[5][8] = 0.301491671718585;
   fWeightMatrix0to1[6][8] = -0.815835166447342;
   fWeightMatrix0to1[7][8] = -0.406843472113614;
   fWeightMatrix0to1[8][8] = 1.57006197808986;
   fWeightMatrix0to1[9][8] = -0.724831627784546;
   fWeightMatrix0to1[10][8] = 0.963168768153087;
   fWeightMatrix0to1[11][8] = -1.04725865621709;
   fWeightMatrix0to1[0][9] = -0.547844250302443;
   fWeightMatrix0to1[1][9] = -1.65996173754803;
   fWeightMatrix0to1[2][9] = 1.80779179000745;
   fWeightMatrix0to1[3][9] = -1.1536208994887;
   fWeightMatrix0to1[4][9] = -0.225077042993424;
   fWeightMatrix0to1[5][9] = 0.457288131788178;
   fWeightMatrix0to1[6][9] = -0.820269118535312;
   fWeightMatrix0to1[7][9] = 0.363342216786131;
   fWeightMatrix0to1[8][9] = -0.673044464535034;
   fWeightMatrix0to1[9][9] = -2.10904226206229;
   fWeightMatrix0to1[10][9] = -1.41802637522869;
   fWeightMatrix0to1[11][9] = 0.206702906237675;
   fWeightMatrix0to1[0][10] = -0.62770409092396;
   fWeightMatrix0to1[1][10] = 0.491810563173041;
   fWeightMatrix0to1[2][10] = 1.69190310225487;
   fWeightMatrix0to1[3][10] = -2.23763677173658;
   fWeightMatrix0to1[4][10] = 0.920294267966316;
   fWeightMatrix0to1[5][10] = -1.30473125402436;
   fWeightMatrix0to1[6][10] = -2.35899063823407;
   fWeightMatrix0to1[7][10] = 0.30553319167342;
   fWeightMatrix0to1[8][10] = -0.0534074784135472;
   fWeightMatrix0to1[9][10] = -1.1096784478478;
   fWeightMatrix0to1[10][10] = -0.934267336068076;
   fWeightMatrix0to1[11][10] = -1.89440801542306;
   fWeightMatrix0to1[0][11] = -1.04113048611061;
   fWeightMatrix0to1[1][11] = -0.176102866321574;
   fWeightMatrix0to1[2][11] = -0.120290728994856;
   fWeightMatrix0to1[3][11] = 0.949557036625155;
   fWeightMatrix0to1[4][11] = 0.9484084307774;
   fWeightMatrix0to1[5][11] = 1.14956084287334;
   fWeightMatrix0to1[6][11] = -1.98484275078501;
   fWeightMatrix0to1[7][11] = -0.500344573640921;
   fWeightMatrix0to1[8][11] = 2.47811703493995;
   fWeightMatrix0to1[9][11] = -1.39155916559325;
   fWeightMatrix0to1[10][11] = 0.0407340779267307;
   fWeightMatrix0to1[11][11] = 0.136089244118214;
   // weight matrix from layer 1 to 2
   fWeightMatrix1to2[0][0] = -1.47322868127709;
   fWeightMatrix1to2[1][0] = 0.243335770106648;
   fWeightMatrix1to2[2][0] = -1.05279835635934;
   fWeightMatrix1to2[3][0] = -0.909381337971985;
   fWeightMatrix1to2[4][0] = -2.01168376824092;
   fWeightMatrix1to2[5][0] = -0.0641519619261345;
   fWeightMatrix1to2[6][0] = 1.58149054268347;
   fWeightMatrix1to2[7][0] = 1.34694459623603;
   fWeightMatrix1to2[8][0] = 1.48146271918256;
   fWeightMatrix1to2[9][0] = -2.59559564551705;
   fWeightMatrix1to2[10][0] = -0.312279153721929;
   fWeightMatrix1to2[0][1] = 0.973548287090749;
   fWeightMatrix1to2[1][1] = -1.57743675257487;
   fWeightMatrix1to2[2][1] = -0.832497119057555;
   fWeightMatrix1to2[3][1] = -0.0597184130100237;
   fWeightMatrix1to2[4][1] = 1.21878260068101;
   fWeightMatrix1to2[5][1] = -1.7181603340952;
   fWeightMatrix1to2[6][1] = -0.744777723933667;
   fWeightMatrix1to2[7][1] = 0.0181159063003982;
   fWeightMatrix1to2[8][1] = -1.50338398341431;
   fWeightMatrix1to2[9][1] = -1.73516657560281;
   fWeightMatrix1to2[10][1] = 0.291161449642245;
   fWeightMatrix1to2[0][2] = 0.56131240495917;
   fWeightMatrix1to2[1][2] = -0.176899554882005;
   fWeightMatrix1to2[2][2] = -1.21693065729406;
   fWeightMatrix1to2[3][2] = -0.15843585336398;
   fWeightMatrix1to2[4][2] = 1.4360424713243;
   fWeightMatrix1to2[5][2] = -0.952945823553856;
   fWeightMatrix1to2[6][2] = 0.911588929168844;
   fWeightMatrix1to2[7][2] = -2.04275390930761;
   fWeightMatrix1to2[8][2] = 0.272059592393452;
   fWeightMatrix1to2[9][2] = -0.111231250252059;
   fWeightMatrix1to2[10][2] = 0.0707389540035337;
   fWeightMatrix1to2[0][3] = -1.33982764015074;
   fWeightMatrix1to2[1][3] = 0.679245903878496;
   fWeightMatrix1to2[2][3] = 1.17418679295537;
   fWeightMatrix1to2[3][3] = -2.12122750863859;
   fWeightMatrix1to2[4][3] = 0.580027995593341;
   fWeightMatrix1to2[5][3] = 0.479894659850369;
   fWeightMatrix1to2[6][3] = 1.04264474406692;
   fWeightMatrix1to2[7][3] = 0.108256668065457;
   fWeightMatrix1to2[8][3] = -1.49827510003813;
   fWeightMatrix1to2[9][3] = -1.89095737441837;
   fWeightMatrix1to2[10][3] = -0.137829137240786;
   fWeightMatrix1to2[0][4] = 0.465165890499185;
   fWeightMatrix1to2[1][4] = 0.344539979186118;
   fWeightMatrix1to2[2][4] = 0.208236736458946;
   fWeightMatrix1to2[3][4] = -0.901541171976458;
   fWeightMatrix1to2[4][4] = 0.618206631376148;
   fWeightMatrix1to2[5][4] = 0.523149422171104;
   fWeightMatrix1to2[6][4] = -1.28516282317132;
   fWeightMatrix1to2[7][4] = 0.0223707312691244;
   fWeightMatrix1to2[8][4] = 0.96846605925089;
   fWeightMatrix1to2[9][4] = 0.074553215692005;
   fWeightMatrix1to2[10][4] = 1.34934959977001;
   fWeightMatrix1to2[0][5] = -0.582451988181287;
   fWeightMatrix1to2[1][5] = 0.609343710724083;
   fWeightMatrix1to2[2][5] = -0.711513067502285;
   fWeightMatrix1to2[3][5] = -0.703453693945482;
   fWeightMatrix1to2[4][5] = -2.19758775137845;
   fWeightMatrix1to2[5][5] = -1.4191232689091;
   fWeightMatrix1to2[6][5] = -1.00019653976958;
   fWeightMatrix1to2[7][5] = 0.142431968585196;
   fWeightMatrix1to2[8][5] = -2.13810324725952;
   fWeightMatrix1to2[9][5] = 1.53233267044637;
   fWeightMatrix1to2[10][5] = -0.820220284791748;
   fWeightMatrix1to2[0][6] = -1.17424267611;
   fWeightMatrix1to2[1][6] = 1.24311778712367;
   fWeightMatrix1to2[2][6] = -1.48701605234596;
   fWeightMatrix1to2[3][6] = -1.93314613838533;
   fWeightMatrix1to2[4][6] = 0.660328282238106;
   fWeightMatrix1to2[5][6] = -0.305711551031584;
   fWeightMatrix1to2[6][6] = 0.0217084824839746;
   fWeightMatrix1to2[7][6] = -2.72168754823776;
   fWeightMatrix1to2[8][6] = -1.10764703983074;
   fWeightMatrix1to2[9][6] = 1.23938192405941;
   fWeightMatrix1to2[10][6] = -3.38262868527497;
   fWeightMatrix1to2[0][7] = 1.09460329279828;
   fWeightMatrix1to2[1][7] = 0.348989947311748;
   fWeightMatrix1to2[2][7] = -0.781242102531765;
   fWeightMatrix1to2[3][7] = -1.29649728870197;
   fWeightMatrix1to2[4][7] = -1.10060969469968;
   fWeightMatrix1to2[5][7] = -0.466667352562041;
   fWeightMatrix1to2[6][7] = -0.746504034328976;
   fWeightMatrix1to2[7][7] = -1.90748801225051;
   fWeightMatrix1to2[8][7] = -0.0427815082590192;
   fWeightMatrix1to2[9][7] = -1.38310254505749;
   fWeightMatrix1to2[10][7] = 1.39223746211525;
   fWeightMatrix1to2[0][8] = -1.6718032863627;
   fWeightMatrix1to2[1][8] = 0.256309208856497;
   fWeightMatrix1to2[2][8] = 0.563945169517476;
   fWeightMatrix1to2[3][8] = 0.702938325824029;
   fWeightMatrix1to2[4][8] = -1.46856261538611;
   fWeightMatrix1to2[5][8] = 1.33242980661474;
   fWeightMatrix1to2[6][8] = -2.23924967341314;
   fWeightMatrix1to2[7][8] = -0.0975215758998997;
   fWeightMatrix1to2[8][8] = -0.379900280045777;
   fWeightMatrix1to2[9][8] = -2.20748895774881;
   fWeightMatrix1to2[10][8] = 1.67494846681109;
   fWeightMatrix1to2[0][9] = -0.266478862654552;
   fWeightMatrix1to2[1][9] = 1.16967966706024;
   fWeightMatrix1to2[2][9] = 1.34690582400945;
   fWeightMatrix1to2[3][9] = -0.000593929063721493;
   fWeightMatrix1to2[4][9] = 1.05881985390228;
   fWeightMatrix1to2[5][9] = -0.923171812082349;
   fWeightMatrix1to2[6][9] = -1.30071469325092;
   fWeightMatrix1to2[7][9] = -0.690033643764885;
   fWeightMatrix1to2[8][9] = -0.726740165762221;
   fWeightMatrix1to2[9][9] = -1.47338546499684;
   fWeightMatrix1to2[10][9] = -1.49213654700723;
   fWeightMatrix1to2[0][10] = 0.900802148584175;
   fWeightMatrix1to2[1][10] = -0.249301911197944;
   fWeightMatrix1to2[2][10] = -1.9497150980127;
   fWeightMatrix1to2[3][10] = 1.1753661875004;
   fWeightMatrix1to2[4][10] = -1.47708171011089;
   fWeightMatrix1to2[5][10] = -0.269721542383481;
   fWeightMatrix1to2[6][10] = -1.35281019621987;
   fWeightMatrix1to2[7][10] = 0.202101861220668;
   fWeightMatrix1to2[8][10] = -0.281393799963119;
   fWeightMatrix1to2[9][10] = -0.482187702017658;
   fWeightMatrix1to2[10][10] = -0.783435797428055;
   fWeightMatrix1to2[0][11] = 0.80309064897014;
   fWeightMatrix1to2[1][11] = -0.292791769683607;
   fWeightMatrix1to2[2][11] = 0.485307387819673;
   fWeightMatrix1to2[3][11] = -1.31531482721169;
   fWeightMatrix1to2[4][11] = -0.717300216978003;
   fWeightMatrix1to2[5][11] = -1.92416007244475;
   fWeightMatrix1to2[6][11] = 0.768007667762561;
   fWeightMatrix1to2[7][11] = 0.948634815157944;
   fWeightMatrix1to2[8][11] = -0.330927312715524;
   fWeightMatrix1to2[9][11] = 1.75553185904996;
   fWeightMatrix1to2[10][11] = 0.123760234216206;
   fWeightMatrix1to2[0][12] = -0.103541959941552;
   fWeightMatrix1to2[1][12] = 0.450387444128983;
   fWeightMatrix1to2[2][12] = -0.700824106313548;
   fWeightMatrix1to2[3][12] = -0.511366336284469;
   fWeightMatrix1to2[4][12] = 1.57658356182719;
   fWeightMatrix1to2[5][12] = 1.2685659628615;
   fWeightMatrix1to2[6][12] = -2.28412929220638;
   fWeightMatrix1to2[7][12] = -2.24500004583237;
   fWeightMatrix1to2[8][12] = 0.231876020019525;
   fWeightMatrix1to2[9][12] = -0.207997711113955;
   fWeightMatrix1to2[10][12] = 1.62289147261988;
   // weight matrix from layer 2 to 3
   fWeightMatrix2to3[0][0] = -0.385380682847755;
   fWeightMatrix2to3[0][1] = 0.27103842709366;
   fWeightMatrix2to3[0][2] = -0.863200440767901;
   fWeightMatrix2to3[0][3] = 0.0559365943420652;
   fWeightMatrix2to3[0][4] = -0.0823087305728585;
   fWeightMatrix2to3[0][5] = -0.801273068771117;
   fWeightMatrix2to3[0][6] = -1.19359837021953;
   fWeightMatrix2to3[0][7] = -0.221760485691592;
   fWeightMatrix2to3[0][8] = 0.906963398647611;
   fWeightMatrix2to3[0][9] = 1.44239093453722;
   fWeightMatrix2to3[0][10] = -0.572789483718738;
   fWeightMatrix2to3[0][11] = 0.813883696526084;
}

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
}