// 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 16:28:18 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: 21486


#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'    [0,0.99990350008]
LRWj                          LRWj                              'F'    [-0.00370291154832,1]
LRZZ                          LRZZ                              'F'    [0,1]
Met                           Met                               'F'    [15.1914625168,199.549758911]
MetDelPhi                     MetDelPhi                         'F'    [0.143834546208,3.13655138016]
MetSpec                       MetSpec                           'F'    [15.0028028488,188.142364502]
dPhiLeptons                   dPhiLeptons                       'F'    [5.24520874023e-06,3.14073061943]
dRLeptons                     dRLeptons                         'F'    [0.401803344488,4.52171230316]
dimass                        dimass                            'F'    [16.0141124725,606.535461426]


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

#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] = 0.999903500080109;
      fVmin[3] = -0.00370291154831648;
      fVmax[3] = 1;
      fVmin[4] = 0;
      fVmax[4] = 1;
      fVmin[5] = 15.1914625167847;
      fVmax[5] = 199.549758911133;
      fVmin[6] = 0.143834546208382;
      fVmax[6] = 3.13655138015747;
      fVmin[7] = 15.0028028488159;
      fVmax[7] = 188.142364501953;
      fVmin[8] = 5.24520874023438e-06;
      fVmax[8] = 3.14073061943054;
      fVmin[9] = 0.401803344488144;
      fVmax[9] = 4.52171230316162;
      fVmin[10] = 16.0141124725342;
      fVmax[10] = 606.535461425781;

      // 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] = 1.60202488528879;
   fWeightMatrix0to1[1][0] = 1.37153998484192;
   fWeightMatrix0to1[2][0] = -0.206602387506984;
   fWeightMatrix0to1[3][0] = 1.02222189561983;
   fWeightMatrix0to1[4][0] = 0.180302819878266;
   fWeightMatrix0to1[5][0] = 2.63901280369413;
   fWeightMatrix0to1[6][0] = 1.99335129679105;
   fWeightMatrix0to1[7][0] = -0.238019920693244;
   fWeightMatrix0to1[8][0] = 1.11009860136848;
   fWeightMatrix0to1[9][0] = 1.22138782391316;
   fWeightMatrix0to1[10][0] = 1.29222543020177;
   fWeightMatrix0to1[11][0] = 1.36857024149885;
   fWeightMatrix0to1[0][1] = 1.1145825194367;
   fWeightMatrix0to1[1][1] = 1.0733177656768;
   fWeightMatrix0to1[2][1] = 1.10589906073832;
   fWeightMatrix0to1[3][1] = -1.90616314833042;
   fWeightMatrix0to1[4][1] = 1.46831211248683;
   fWeightMatrix0to1[5][1] = 0.172627210504629;
   fWeightMatrix0to1[6][1] = -1.04551669163545;
   fWeightMatrix0to1[7][1] = 1.74464893067914;
   fWeightMatrix0to1[8][1] = 2.44093728618836;
   fWeightMatrix0to1[9][1] = 1.32812670558431;
   fWeightMatrix0to1[10][1] = 0.217950873886736;
   fWeightMatrix0to1[11][1] = -1.01988316747294;
   fWeightMatrix0to1[0][2] = 0.462182508480596;
   fWeightMatrix0to1[1][2] = -0.0911553940070854;
   fWeightMatrix0to1[2][2] = 0.0172475116367192;
   fWeightMatrix0to1[3][2] = -1.70297230257398;
   fWeightMatrix0to1[4][2] = 1.56966377775935;
   fWeightMatrix0to1[5][2] = -0.222950695769698;
   fWeightMatrix0to1[6][2] = -0.261750333717998;
   fWeightMatrix0to1[7][2] = -0.72417013271158;
   fWeightMatrix0to1[8][2] = -0.185920353174587;
   fWeightMatrix0to1[9][2] = -0.547390170230584;
   fWeightMatrix0to1[10][2] = -0.235318779261035;
   fWeightMatrix0to1[11][2] = 1.47011628968466;
   fWeightMatrix0to1[0][3] = 0.567497996599294;
   fWeightMatrix0to1[1][3] = 0.585563715120258;
   fWeightMatrix0to1[2][3] = 1.23524070652342;
   fWeightMatrix0to1[3][3] = 1.42117741941135;
   fWeightMatrix0to1[4][3] = -1.05771471533766;
   fWeightMatrix0to1[5][3] = -0.909036471216505;
   fWeightMatrix0to1[6][3] = -0.238720981261707;
   fWeightMatrix0to1[7][3] = -1.92510652857268;
   fWeightMatrix0to1[8][3] = -0.449129968892899;
   fWeightMatrix0to1[9][3] = -1.5701593618778;
   fWeightMatrix0to1[10][3] = -0.118006795930995;
   fWeightMatrix0to1[11][3] = 1.16357215916554;
   fWeightMatrix0to1[0][4] = 0.695357452802014;
   fWeightMatrix0to1[1][4] = -0.678241281772734;
   fWeightMatrix0to1[2][4] = 1.0417587076114;
   fWeightMatrix0to1[3][4] = -1.50402128898845;
   fWeightMatrix0to1[4][4] = 0.0959260538259567;
   fWeightMatrix0to1[5][4] = -0.868648984458747;
   fWeightMatrix0to1[6][4] = -0.98534717215807;
   fWeightMatrix0to1[7][4] = 0.0344252976919689;
   fWeightMatrix0to1[8][4] = -0.612103725406909;
   fWeightMatrix0to1[9][4] = 0.508777297604143;
   fWeightMatrix0to1[10][4] = 0.0769654690977995;
   fWeightMatrix0to1[11][4] = -0.331673337041849;
   fWeightMatrix0to1[0][5] = -1.07872025131487;
   fWeightMatrix0to1[1][5] = 0.531712813988417;
   fWeightMatrix0to1[2][5] = -2.08357082233969;
   fWeightMatrix0to1[3][5] = 0.511077794816647;
   fWeightMatrix0to1[4][5] = 0.730591326718377;
   fWeightMatrix0to1[5][5] = -2.11900929804547;
   fWeightMatrix0to1[6][5] = 0.940525114502817;
   fWeightMatrix0to1[7][5] = -0.418715881486912;
   fWeightMatrix0to1[8][5] = 0.316842176440395;
   fWeightMatrix0to1[9][5] = 0.608039890048736;
   fWeightMatrix0to1[10][5] = 0.362533936259384;
   fWeightMatrix0to1[11][5] = -0.88291641612719;
   fWeightMatrix0to1[0][6] = -1.10909555417684;
   fWeightMatrix0to1[1][6] = -1.41623669020788;
   fWeightMatrix0to1[2][6] = 1.30352375514459;
   fWeightMatrix0to1[3][6] = -0.982489435598934;
   fWeightMatrix0to1[4][6] = -0.139602011977239;
   fWeightMatrix0to1[5][6] = -0.986344546001909;
   fWeightMatrix0to1[6][6] = -2.67744019192771;
   fWeightMatrix0to1[7][6] = 1.43150396307703;
   fWeightMatrix0to1[8][6] = 0.373099623498785;
   fWeightMatrix0to1[9][6] = 0.894570620211401;
   fWeightMatrix0to1[10][6] = 2.20896624976744;
   fWeightMatrix0to1[11][6] = 0.78692365228047;
   fWeightMatrix0to1[0][7] = -0.654284352663636;
   fWeightMatrix0to1[1][7] = 1.10426405089876;
   fWeightMatrix0to1[2][7] = 1.75504027196616;
   fWeightMatrix0to1[3][7] = -0.783698825809501;
   fWeightMatrix0to1[4][7] = 0.995807565952242;
   fWeightMatrix0to1[5][7] = -0.299062267923051;
   fWeightMatrix0to1[6][7] = 0.0105899498331152;
   fWeightMatrix0to1[7][7] = -0.446635075656651;
   fWeightMatrix0to1[8][7] = 0.0744220541925907;
   fWeightMatrix0to1[9][7] = 1.72313579860626;
   fWeightMatrix0to1[10][7] = -0.452045090965562;
   fWeightMatrix0to1[11][7] = 2.41539906514047;
   fWeightMatrix0to1[0][8] = -0.609628721725797;
   fWeightMatrix0to1[1][8] = -1.11034139997077;
   fWeightMatrix0to1[2][8] = 2.06440989365604;
   fWeightMatrix0to1[3][8] = -1.92807347802307;
   fWeightMatrix0to1[4][8] = 0.554291181067865;
   fWeightMatrix0to1[5][8] = 0.60869871415442;
   fWeightMatrix0to1[6][8] = -0.0760054443239105;
   fWeightMatrix0to1[7][8] = -0.474789462419459;
   fWeightMatrix0to1[8][8] = 2.06027680552804;
   fWeightMatrix0to1[9][8] = -0.325415058146514;
   fWeightMatrix0to1[10][8] = 0.307974855686314;
   fWeightMatrix0to1[11][8] = -0.676544680702478;
   fWeightMatrix0to1[0][9] = -0.209948080687368;
   fWeightMatrix0to1[1][9] = -2.24743916437538;
   fWeightMatrix0to1[2][9] = 2.0758680905246;
   fWeightMatrix0to1[3][9] = -1.3619458708188;
   fWeightMatrix0to1[4][9] = 0.667675691599695;
   fWeightMatrix0to1[5][9] = 0.43502259630326;
   fWeightMatrix0to1[6][9] = -0.560065408957576;
   fWeightMatrix0to1[7][9] = 0.634960231892051;
   fWeightMatrix0to1[8][9] = -0.747568229177485;
   fWeightMatrix0to1[9][9] = -2.17968237875093;
   fWeightMatrix0to1[10][9] = -1.52025020062209;
   fWeightMatrix0to1[11][9] = 0.54461998681323;
   fWeightMatrix0to1[0][10] = -0.542658392867209;
   fWeightMatrix0to1[1][10] = 0.971647007775896;
   fWeightMatrix0to1[2][10] = 1.39619417387192;
   fWeightMatrix0to1[3][10] = -2.08740915949364;
   fWeightMatrix0to1[4][10] = 0.985915894171224;
   fWeightMatrix0to1[5][10] = -1.7334198527299;
   fWeightMatrix0to1[6][10] = -1.96316200653664;
   fWeightMatrix0to1[7][10] = 0.800977703873895;
   fWeightMatrix0to1[8][10] = -0.30787235696974;
   fWeightMatrix0to1[9][10] = -1.01897725458524;
   fWeightMatrix0to1[10][10] = -1.90222510584003;
   fWeightMatrix0to1[11][10] = -1.26575026583534;
   fWeightMatrix0to1[0][11] = -1.13761985786775;
   fWeightMatrix0to1[1][11] = -0.822183684240504;
   fWeightMatrix0to1[2][11] = 0.0180501757062828;
   fWeightMatrix0to1[3][11] = 1.38896959566906;
   fWeightMatrix0to1[4][11] = 1.55857338020507;
   fWeightMatrix0to1[5][11] = 1.16652622258107;
   fWeightMatrix0to1[6][11] = -1.45726166258669;
   fWeightMatrix0to1[7][11] = -1.4404606775281;
   fWeightMatrix0to1[8][11] = 3.12319488959208;
   fWeightMatrix0to1[9][11] = -1.5797892884316;
   fWeightMatrix0to1[10][11] = -0.0307374729687434;
   fWeightMatrix0to1[11][11] = -0.598159640858692;
   // weight matrix from layer 1 to 2
   fWeightMatrix1to2[0][0] = -1.44390248699727;
   fWeightMatrix1to2[1][0] = 0.144053283358076;
   fWeightMatrix1to2[2][0] = -0.899449577728178;
   fWeightMatrix1to2[3][0] = -0.892862684745961;
   fWeightMatrix1to2[4][0] = -2.11793671138925;
   fWeightMatrix1to2[5][0] = 0.723363756540363;
   fWeightMatrix1to2[6][0] = 1.76603172266598;
   fWeightMatrix1to2[7][0] = 1.53095985917761;
   fWeightMatrix1to2[8][0] = 1.66156559072622;
   fWeightMatrix1to2[9][0] = -2.11749620902932;
   fWeightMatrix1to2[10][0] = -0.520222731639929;
   fWeightMatrix1to2[0][1] = 0.918159979935365;
   fWeightMatrix1to2[1][1] = -1.68477945017206;
   fWeightMatrix1to2[2][1] = -0.985735017980359;
   fWeightMatrix1to2[3][1] = -0.0679311773554322;
   fWeightMatrix1to2[4][1] = 1.2032815487021;
   fWeightMatrix1to2[5][1] = -2.28598128405602;
   fWeightMatrix1to2[6][1] = -0.951767654327175;
   fWeightMatrix1to2[7][1] = 0.0416625180714081;
   fWeightMatrix1to2[8][1] = -1.38625950173559;
   fWeightMatrix1to2[9][1] = -1.29611036306735;
   fWeightMatrix1to2[10][1] = -0.052808298079043;
   fWeightMatrix1to2[0][2] = 0.569495316564171;
   fWeightMatrix1to2[1][2] = -0.279717129647365;
   fWeightMatrix1to2[2][2] = -1.58538538783118;
   fWeightMatrix1to2[3][2] = -0.157536493932877;
   fWeightMatrix1to2[4][2] = 1.63676108877117;
   fWeightMatrix1to2[5][2] = -0.0577006357929955;
   fWeightMatrix1to2[6][2] = 1.04119297335105;
   fWeightMatrix1to2[7][2] = -2.03873594218162;
   fWeightMatrix1to2[8][2] = 0.275964789265028;
   fWeightMatrix1to2[9][2] = -0.154362562565193;
   fWeightMatrix1to2[10][2] = -0.170902755175201;
   fWeightMatrix1to2[0][3] = -1.41550479924087;
   fWeightMatrix1to2[1][3] = 0.15115875544677;
   fWeightMatrix1to2[2][3] = 1.07582598844466;
   fWeightMatrix1to2[3][3] = -2.16564601838452;
   fWeightMatrix1to2[4][3] = 0.445433195589241;
   fWeightMatrix1to2[5][3] = 0.0463821493045683;
   fWeightMatrix1to2[6][3] = 1.279591248883;
   fWeightMatrix1to2[7][3] = 0.0672848691216471;
   fWeightMatrix1to2[8][3] = -1.60359064681211;
   fWeightMatrix1to2[9][3] = -1.84530373446499;
   fWeightMatrix1to2[10][3] = -0.614736187728743;
   fWeightMatrix1to2[0][4] = 0.341421219394221;
   fWeightMatrix1to2[1][4] = -0.0175688845015356;
   fWeightMatrix1to2[2][4] = -0.0718334317898256;
   fWeightMatrix1to2[3][4] = -1.06765709654168;
   fWeightMatrix1to2[4][4] = 0.367754228335443;
   fWeightMatrix1to2[5][4] = 1.14329219038039;
   fWeightMatrix1to2[6][4] = -1.37966991590769;
   fWeightMatrix1to2[7][4] = -0.218254469638079;
   fWeightMatrix1to2[8][4] = 0.762313983098308;
   fWeightMatrix1to2[9][4] = 0.25349433804128;
   fWeightMatrix1to2[10][4] = -0.153101720535356;
   fWeightMatrix1to2[0][5] = -0.58198159114623;
   fWeightMatrix1to2[1][5] = 0.0962955415486077;
   fWeightMatrix1to2[2][5] = -0.653572849472981;
   fWeightMatrix1to2[3][5] = -0.742027461355096;
   fWeightMatrix1to2[4][5] = -2.20741982625346;
   fWeightMatrix1to2[5][5] = -1.26401551302733;
   fWeightMatrix1to2[6][5] = -0.862518366224157;
   fWeightMatrix1to2[7][5] = 0.100549779005898;
   fWeightMatrix1to2[8][5] = -2.09098746692932;
   fWeightMatrix1to2[9][5] = 1.62609581062098;
   fWeightMatrix1to2[10][5] = -0.98882053741829;
   fWeightMatrix1to2[0][6] = -1.16798068267479;
   fWeightMatrix1to2[1][6] = 1.00340929573182;
   fWeightMatrix1to2[2][6] = -1.35334217444077;
   fWeightMatrix1to2[3][6] = -1.93065972460268;
   fWeightMatrix1to2[4][6] = 0.667977908877992;
   fWeightMatrix1to2[5][6] = -1.72509087691684;
   fWeightMatrix1to2[6][6] = 0.718487079403886;
   fWeightMatrix1to2[7][6] = -2.65153880654993;
   fWeightMatrix1to2[8][6] = -0.955169765915787;
   fWeightMatrix1to2[9][6] = 0.6499951865469;
   fWeightMatrix1to2[10][6] = -3.10398032484893;
   fWeightMatrix1to2[0][7] = 1.09201832961266;
   fWeightMatrix1to2[1][7] = 0.272758207731386;
   fWeightMatrix1to2[2][7] = -1.18953960959152;
   fWeightMatrix1to2[3][7] = -1.26407613268897;
   fWeightMatrix1to2[4][7] = -1.21882103545016;
   fWeightMatrix1to2[5][7] = -0.301220564578962;
   fWeightMatrix1to2[6][7] = -0.704562248523765;
   fWeightMatrix1to2[7][7] = -1.93649078565364;
   fWeightMatrix1to2[8][7] = 0.0118003744601894;
   fWeightMatrix1to2[9][7] = -1.09223926735438;
   fWeightMatrix1to2[10][7] = 0.896644566894294;
   fWeightMatrix1to2[0][8] = -1.62497105920969;
   fWeightMatrix1to2[1][8] = -0.420689453361637;
   fWeightMatrix1to2[2][8] = 1.02162245457879;
   fWeightMatrix1to2[3][8] = 0.642047942997396;
   fWeightMatrix1to2[4][8] = -1.51150968203808;
   fWeightMatrix1to2[5][8] = 2.2713083036336;
   fWeightMatrix1to2[6][8] = -2.01542457913149;
   fWeightMatrix1to2[7][8] = 0.0569822860580738;
   fWeightMatrix1to2[8][8] = -0.636431484066979;
   fWeightMatrix1to2[9][8] = -2.24792165718565;
   fWeightMatrix1to2[10][8] = 1.03861745750606;
   fWeightMatrix1to2[0][9] = -0.395494060581187;
   fWeightMatrix1to2[1][9] = 0.949838341993549;
   fWeightMatrix1to2[2][9] = 1.10365654264673;
   fWeightMatrix1to2[3][9] = 0.0489544947387866;
   fWeightMatrix1to2[4][9] = 1.00378993849117;
   fWeightMatrix1to2[5][9] = -0.928198402509864;
   fWeightMatrix1to2[6][9] = -1.229857245721;
   fWeightMatrix1to2[7][9] = -0.567736390887254;
   fWeightMatrix1to2[8][9] = -0.583298747641505;
   fWeightMatrix1to2[9][9] = -1.21821449875529;
   fWeightMatrix1to2[10][9] = -0.353843666843441;
   fWeightMatrix1to2[0][10] = 0.784347341030798;
   fWeightMatrix1to2[1][10] = -0.683911500608627;
   fWeightMatrix1to2[2][10] = -1.90700255604345;
   fWeightMatrix1to2[3][10] = 1.18068826803043;
   fWeightMatrix1to2[4][10] = -1.51907333381366;
   fWeightMatrix1to2[5][10] = -1.14452076760072;
   fWeightMatrix1to2[6][10] = -1.45906990149579;
   fWeightMatrix1to2[7][10] = 0.217664613140259;
   fWeightMatrix1to2[8][10] = -0.313884033009556;
   fWeightMatrix1to2[9][10] = -0.38468649356597;
   fWeightMatrix1to2[10][10] = -1.07644049917756;
   fWeightMatrix1to2[0][11] = 0.807587626380901;
   fWeightMatrix1to2[1][11] = -0.394633261777069;
   fWeightMatrix1to2[2][11] = 0.198000449067015;
   fWeightMatrix1to2[3][11] = -1.27559350376789;
   fWeightMatrix1to2[4][11] = -0.761352774063405;
   fWeightMatrix1to2[5][11] = -1.69385950354516;
   fWeightMatrix1to2[6][11] = 0.791998859365806;
   fWeightMatrix1to2[7][11] = 0.94794570157561;
   fWeightMatrix1to2[8][11] = -0.359213871536133;
   fWeightMatrix1to2[9][11] = 1.29931455200827;
   fWeightMatrix1to2[10][11] = 0.911411250498975;
   fWeightMatrix1to2[0][12] = -0.209945438236411;
   fWeightMatrix1to2[1][12] = -0.130943704463641;
   fWeightMatrix1to2[2][12] = -0.591224130627158;
   fWeightMatrix1to2[3][12] = -0.549314514694959;
   fWeightMatrix1to2[4][12] = 1.4509077710142;
   fWeightMatrix1to2[5][12] = 1.66946721140785;
   fWeightMatrix1to2[6][12] = -2.02792310340673;
   fWeightMatrix1to2[7][12] = -2.25934540958845;
   fWeightMatrix1to2[8][12] = -0.0118772428763881;
   fWeightMatrix1to2[9][12] = -0.22556011133757;
   fWeightMatrix1to2[10][12] = 0.663012510336852;
   // weight matrix from layer 2 to 3
   fWeightMatrix2to3[0][0] = -0.0489152900329682;
   fWeightMatrix2to3[0][1] = 0.0302660081172627;
   fWeightMatrix2to3[0][2] = -1.0516588251224;
   fWeightMatrix2to3[0][3] = -0.0372827478424661;
   fWeightMatrix2to3[0][4] = 0.270062617835979;
   fWeightMatrix2to3[0][5] = -0.732930489357967;
   fWeightMatrix2to3[0][6] = -1.49255938441804;
   fWeightMatrix2to3[0][7] = -0.0802877875590936;
   fWeightMatrix2to3[0][8] = 0.410796539470536;
   fWeightMatrix2to3[0][9] = 0.749266697055274;
   fWeightMatrix2to3[0][10] = -0.501374424157965;
   fWeightMatrix2to3[0][11] = 0.965444032104413;
}

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
}