// 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 16:16:23 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: 15118


#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'    [1.1345506428e-34,1.001734972]
LRWg                          LRWg                              'F'    [0,0.999915719032]
LRWj                          LRWj                              'F'    [-0.00173494115006,1]
LRZZ                          LRZZ                              'F'    [0,1]
Met                           Met                               'F'    [15.1351919174,204.075332642]
MetDelPhi                     MetDelPhi                         'F'    [0.143834546208,3.13630962372]
MetSpec                       MetSpec                           'F'    [15.0015153885,153.344940186]
dPhiLeptons                   dPhiLeptons                       'F'    [7.39097595215e-05,3.14107751846]
dRLeptons                     dRLeptons                         'F'    [0.415245831013,4.52171230316]
dimass                        dimass                            'F'    [16.0030345917,490.262542725]


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

#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] = 1.13455064280395e-34;
      fVmax[1] = 1.00173497200012;
      fVmin[2] = 0;
      fVmax[2] = 0.999915719032288;
      fVmin[3] = -0.00173494115006179;
      fVmax[3] = 1;
      fVmin[4] = 0;
      fVmax[4] = 1;
      fVmin[5] = 15.1351919174194;
      fVmax[5] = 204.075332641602;
      fVmin[6] = 0.143834546208382;
      fVmax[6] = 3.13630962371826;
      fVmin[7] = 15.0015153884888;
      fVmax[7] = 153.344940185547;
      fVmin[8] = 7.39097595214844e-05;
      fVmax[8] = 3.14107751846313;
      fVmin[9] = 0.415245831012726;
      fVmax[9] = 4.52171230316162;
      fVmin[10] = 16.0030345916748;
      fVmax[10] = 490.262542724609;

      // 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] = 1.93203759799319;
   fWeightMatrix0to1[1][0] = 1.91912635636299;
   fWeightMatrix0to1[2][0] = -0.392113958479782;
   fWeightMatrix0to1[3][0] = 1.90938116937255;
   fWeightMatrix0to1[4][0] = 0.610967390316145;
   fWeightMatrix0to1[5][0] = 3.98901145643896;
   fWeightMatrix0to1[6][0] = 1.04713349754688;
   fWeightMatrix0to1[7][0] = -0.956899689819063;
   fWeightMatrix0to1[8][0] = 0.584368982078557;
   fWeightMatrix0to1[9][0] = 1.64473375809677;
   fWeightMatrix0to1[10][0] = 1.06779022329932;
   fWeightMatrix0to1[11][0] = -0.270809143454584;
   fWeightMatrix0to1[0][1] = 1.46964274325752;
   fWeightMatrix0to1[1][1] = 1.19344113113818;
   fWeightMatrix0to1[2][1] = 1.37360108449053;
   fWeightMatrix0to1[3][1] = -2.01361149127138;
   fWeightMatrix0to1[4][1] = 1.13986238153604;
   fWeightMatrix0to1[5][1] = -0.0224775775457241;
   fWeightMatrix0to1[6][1] = -1.19321280017954;
   fWeightMatrix0to1[7][1] = 1.16080191109432;
   fWeightMatrix0to1[8][1] = 1.78542792871395;
   fWeightMatrix0to1[9][1] = 1.38404108411049;
   fWeightMatrix0to1[10][1] = 0.523486664440577;
   fWeightMatrix0to1[11][1] = -0.527290417011897;
   fWeightMatrix0to1[0][2] = 0.49844960663685;
   fWeightMatrix0to1[1][2] = 1.55074378275813;
   fWeightMatrix0to1[2][2] = -0.073639068536119;
   fWeightMatrix0to1[3][2] = -1.59282708951474;
   fWeightMatrix0to1[4][2] = 1.99733963889759;
   fWeightMatrix0to1[5][2] = -0.42487313575433;
   fWeightMatrix0to1[6][2] = -0.0841734716844268;
   fWeightMatrix0to1[7][2] = -0.836107363138932;
   fWeightMatrix0to1[8][2] = -1.06162923622238;
   fWeightMatrix0to1[9][2] = -0.976739890599993;
   fWeightMatrix0to1[10][2] = -1.16616702215691;
   fWeightMatrix0to1[11][2] = 0.228776462736159;
   fWeightMatrix0to1[0][3] = 0.412609358737418;
   fWeightMatrix0to1[1][3] = 0.527446881382355;
   fWeightMatrix0to1[2][3] = 1.24237402871057;
   fWeightMatrix0to1[3][3] = 1.50763314827473;
   fWeightMatrix0to1[4][3] = -1.12357059639701;
   fWeightMatrix0to1[5][3] = -0.24010257730797;
   fWeightMatrix0to1[6][3] = -0.46243139907571;
   fWeightMatrix0to1[7][3] = -1.17901057303199;
   fWeightMatrix0to1[8][3] = -0.298984698723075;
   fWeightMatrix0to1[9][3] = -1.03557853595708;
   fWeightMatrix0to1[10][3] = 0.547826547254072;
   fWeightMatrix0to1[11][3] = 1.35478763253096;
   fWeightMatrix0to1[0][4] = 0.325817608715079;
   fWeightMatrix0to1[1][4] = -0.237726482405437;
   fWeightMatrix0to1[2][4] = 0.979755959798609;
   fWeightMatrix0to1[3][4] = -0.606392777100619;
   fWeightMatrix0to1[4][4] = -0.252586863312885;
   fWeightMatrix0to1[5][4] = -0.716491389818989;
   fWeightMatrix0to1[6][4] = -0.177094231973646;
   fWeightMatrix0to1[7][4] = 0.476685067497817;
   fWeightMatrix0to1[8][4] = -0.30612121669194;
   fWeightMatrix0to1[9][4] = 0.488151334752025;
   fWeightMatrix0to1[10][4] = -0.28139262660489;
   fWeightMatrix0to1[11][4] = -0.215152781691154;
   fWeightMatrix0to1[0][5] = -0.740909959824854;
   fWeightMatrix0to1[1][5] = -0.542742566904397;
   fWeightMatrix0to1[2][5] = -1.84909213983838;
   fWeightMatrix0to1[3][5] = 0.600611709530786;
   fWeightMatrix0to1[4][5] = 0.935618041219675;
   fWeightMatrix0to1[5][5] = -1.51687495022817;
   fWeightMatrix0to1[6][5] = 1.51652918822746;
   fWeightMatrix0to1[7][5] = -0.324809537702203;
   fWeightMatrix0to1[8][5] = -0.407477986298439;
   fWeightMatrix0to1[9][5] = 0.112193261177526;
   fWeightMatrix0to1[10][5] = 0.308532888867332;
   fWeightMatrix0to1[11][5] = -0.500262250228886;
   fWeightMatrix0to1[0][6] = -1.02416508151962;
   fWeightMatrix0to1[1][6] = 0.161368935928657;
   fWeightMatrix0to1[2][6] = 0.802879510848575;
   fWeightMatrix0to1[3][6] = -1.13455606716027;
   fWeightMatrix0to1[4][6] = -0.178834123593322;
   fWeightMatrix0to1[5][6] = -0.306863698258807;
   fWeightMatrix0to1[6][6] = -1.50607398793705;
   fWeightMatrix0to1[7][6] = 1.49811768288744;
   fWeightMatrix0to1[8][6] = -0.169922166761373;
   fWeightMatrix0to1[9][6] = 1.5822337523983;
   fWeightMatrix0to1[10][6] = 1.25357713345991;
   fWeightMatrix0to1[11][6] = 0.910094113161994;
   fWeightMatrix0to1[0][7] = -0.570587216268508;
   fWeightMatrix0to1[1][7] = 0.650571458015519;
   fWeightMatrix0to1[2][7] = 1.89289256678143;
   fWeightMatrix0to1[3][7] = -0.480251691650232;
   fWeightMatrix0to1[4][7] = 1.26999742460296;
   fWeightMatrix0to1[5][7] = -0.655074197106109;
   fWeightMatrix0to1[6][7] = -0.403463943575848;
   fWeightMatrix0to1[7][7] = -0.338636167877171;
   fWeightMatrix0to1[8][7] = -0.112894843486339;
   fWeightMatrix0to1[9][7] = 1.50221031248101;
   fWeightMatrix0to1[10][7] = -1.26073740190984;
   fWeightMatrix0to1[11][7] = 2.89433038450622;
   fWeightMatrix0to1[0][8] = -0.643775205527979;
   fWeightMatrix0to1[1][8] = -0.38092938140884;
   fWeightMatrix0to1[2][8] = 1.90653863631467;
   fWeightMatrix0to1[3][8] = -1.97009023547058;
   fWeightMatrix0to1[4][8] = -0.145859253951973;
   fWeightMatrix0to1[5][8] = -0.125035754237898;
   fWeightMatrix0to1[6][8] = -0.794175773959813;
   fWeightMatrix0to1[7][8] = -0.343581778867436;
   fWeightMatrix0to1[8][8] = 1.43275816850124;
   fWeightMatrix0to1[9][8] = -0.300443074787136;
   fWeightMatrix0to1[10][8] = 1.61817300181778;
   fWeightMatrix0to1[11][8] = -0.769556970656873;
   fWeightMatrix0to1[0][9] = 0.237553743656175;
   fWeightMatrix0to1[1][9] = -1.45448744852972;
   fWeightMatrix0to1[2][9] = 1.95864849754126;
   fWeightMatrix0to1[3][9] = -1.13362821836721;
   fWeightMatrix0to1[4][9] = -0.20236304158674;
   fWeightMatrix0to1[5][9] = -0.100873457462269;
   fWeightMatrix0to1[6][9] = -0.562916394356626;
   fWeightMatrix0to1[7][9] = 1.07902990020386;
   fWeightMatrix0to1[8][9] = -0.83103257152355;
   fWeightMatrix0to1[9][9] = -1.98453733210181;
   fWeightMatrix0to1[10][9] = -1.08995626322397;
   fWeightMatrix0to1[11][9] = 0.130313616191456;
   fWeightMatrix0to1[0][10] = -0.437932799145754;
   fWeightMatrix0to1[1][10] = 0.708218779363563;
   fWeightMatrix0to1[2][10] = 1.76458731865496;
   fWeightMatrix0to1[3][10] = -1.87237378358298;
   fWeightMatrix0to1[4][10] = 0.883026214261302;
   fWeightMatrix0to1[5][10] = -1.58737611838717;
   fWeightMatrix0to1[6][10] = -3.66620129589852;
   fWeightMatrix0to1[7][10] = 0.998865934715779;
   fWeightMatrix0to1[8][10] = -0.111072088660156;
   fWeightMatrix0to1[9][10] = -1.25727834395552;
   fWeightMatrix0to1[10][10] = -1.26426824219477;
   fWeightMatrix0to1[11][10] = -1.24982527692549;
   fWeightMatrix0to1[0][11] = -1.15894310080138;
   fWeightMatrix0to1[1][11] = -0.410346088541016;
   fWeightMatrix0to1[2][11] = -0.287618459598496;
   fWeightMatrix0to1[3][11] = 0.618089812538713;
   fWeightMatrix0to1[4][11] = 1.18391149096874;
   fWeightMatrix0to1[5][11] = 1.07752015299047;
   fWeightMatrix0to1[6][11] = -2.43894161912399;
   fWeightMatrix0to1[7][11] = -1.18703565321713;
   fWeightMatrix0to1[8][11] = 2.6384177554558;
   fWeightMatrix0to1[9][11] = -1.44301262223822;
   fWeightMatrix0to1[10][11] = 0.543794347940731;
   fWeightMatrix0to1[11][11] = -0.414609410484118;
   // weight matrix from layer 1 to 2
   fWeightMatrix1to2[0][0] = -1.76018492150111;
   fWeightMatrix1to2[1][0] = 0.389414358640214;
   fWeightMatrix1to2[2][0] = -1.00899974081007;
   fWeightMatrix1to2[3][0] = -0.815426006637787;
   fWeightMatrix1to2[4][0] = -2.25784795374289;
   fWeightMatrix1to2[5][0] = 0.921066145000764;
   fWeightMatrix1to2[6][0] = 1.41768165263817;
   fWeightMatrix1to2[7][0] = 1.38302117170495;
   fWeightMatrix1to2[8][0] = 1.62474891737382;
   fWeightMatrix1to2[9][0] = -2.4973191251141;
   fWeightMatrix1to2[10][0] = -0.54302142505725;
   fWeightMatrix1to2[0][1] = 0.641026197523823;
   fWeightMatrix1to2[1][1] = -1.48447834706022;
   fWeightMatrix1to2[2][1] = -0.713669102073791;
   fWeightMatrix1to2[3][1] = -0.0402796670707248;
   fWeightMatrix1to2[4][1] = 1.20028989029587;
   fWeightMatrix1to2[5][1] = -1.86908141564337;
   fWeightMatrix1to2[6][1] = -0.93842502301962;
   fWeightMatrix1to2[7][1] = -0.0450266049999273;
   fWeightMatrix1to2[8][1] = -1.16922225563281;
   fWeightMatrix1to2[9][1] = -2.07699535001575;
   fWeightMatrix1to2[10][1] = 0.303964983913458;
   fWeightMatrix1to2[0][2] = 0.614282768176175;
   fWeightMatrix1to2[1][2] = -0.152083252956299;
   fWeightMatrix1to2[2][2] = -1.07804167001128;
   fWeightMatrix1to2[3][2] = -0.114541973148773;
   fWeightMatrix1to2[4][2] = 1.12351978788052;
   fWeightMatrix1to2[5][2] = -1.07012030222861;
   fWeightMatrix1to2[6][2] = 0.884086591338557;
   fWeightMatrix1to2[7][2] = -2.03679444359884;
   fWeightMatrix1to2[8][2] = 0.190893089851754;
   fWeightMatrix1to2[9][2] = -0.0719501479458695;
   fWeightMatrix1to2[10][2] = -0.304448378794587;
   fWeightMatrix1to2[0][3] = -1.33991539700354;
   fWeightMatrix1to2[1][3] = 0.876767235482547;
   fWeightMatrix1to2[2][3] = 1.16285891912031;
   fWeightMatrix1to2[3][3] = -2.04235102014539;
   fWeightMatrix1to2[4][3] = 0.65525250258936;
   fWeightMatrix1to2[5][3] = 0.27957501331953;
   fWeightMatrix1to2[6][3] = 1.14019236858607;
   fWeightMatrix1to2[7][3] = 0.196044687720233;
   fWeightMatrix1to2[8][3] = -1.13349666108454;
   fWeightMatrix1to2[9][3] = -1.77184661664192;
   fWeightMatrix1to2[10][3] = 0.01477614157379;
   fWeightMatrix1to2[0][4] = 0.0748117025756278;
   fWeightMatrix1to2[1][4] = 0.440318145197076;
   fWeightMatrix1to2[2][4] = 0.109373321949896;
   fWeightMatrix1to2[3][4] = -0.94395622341143;
   fWeightMatrix1to2[4][4] = 0.611806775768655;
   fWeightMatrix1to2[5][4] = 0.17460506402621;
   fWeightMatrix1to2[6][4] = -1.37163649440483;
   fWeightMatrix1to2[7][4] = -0.105083196919337;
   fWeightMatrix1to2[8][4] = 0.974362170391051;
   fWeightMatrix1to2[9][4] = -0.587817942551025;
   fWeightMatrix1to2[10][4] = 0.494750175740208;
   fWeightMatrix1to2[0][5] = -0.355868797990522;
   fWeightMatrix1to2[1][5] = 0.79846637030286;
   fWeightMatrix1to2[2][5] = -0.301317740464462;
   fWeightMatrix1to2[3][5] = -0.470774353287799;
   fWeightMatrix1to2[4][5] = -2.10205945885006;
   fWeightMatrix1to2[5][5] = -0.941291976517847;
   fWeightMatrix1to2[6][5] = -1.01517713065258;
   fWeightMatrix1to2[7][5] = 0.366903301312326;
   fWeightMatrix1to2[8][5] = -2.30991532948079;
   fWeightMatrix1to2[9][5] = 1.51449865833333;
   fWeightMatrix1to2[10][5] = -1.19139712081949;
   fWeightMatrix1to2[0][6] = -1.14081935226427;
   fWeightMatrix1to2[1][6] = 1.38350690751553;
   fWeightMatrix1to2[2][6] = -1.25454546236917;
   fWeightMatrix1to2[3][6] = -1.82473310850187;
   fWeightMatrix1to2[4][6] = 0.649274024831305;
   fWeightMatrix1to2[5][6] = -0.362544145589969;
   fWeightMatrix1to2[6][6] = -0.28380052836361;
   fWeightMatrix1to2[7][6] = -2.53681588776429;
   fWeightMatrix1to2[8][6] = -1.25643135107893;
   fWeightMatrix1to2[9][6] = 1.78228850153431;
   fWeightMatrix1to2[10][6] = -3.79000825863181;
   fWeightMatrix1to2[0][7] = 1.30541655269081;
   fWeightMatrix1to2[1][7] = 0.609669952767645;
   fWeightMatrix1to2[2][7] = -0.997894429776477;
   fWeightMatrix1to2[3][7] = -1.05112890871595;
   fWeightMatrix1to2[4][7] = -1.32437858770468;
   fWeightMatrix1to2[5][7] = -0.953717071555572;
   fWeightMatrix1to2[6][7] = -0.827524604245094;
   fWeightMatrix1to2[7][7] = -1.78685707522461;
   fWeightMatrix1to2[8][7] = -0.401958605310761;
   fWeightMatrix1to2[9][7] = -1.13144432949552;
   fWeightMatrix1to2[10][7] = 0.982098067108535;
   fWeightMatrix1to2[0][8] = -1.51681397527687;
   fWeightMatrix1to2[1][8] = 0.486858955773257;
   fWeightMatrix1to2[2][8] = 0.554801189685408;
   fWeightMatrix1to2[3][8] = 0.804493536567536;
   fWeightMatrix1to2[4][8] = -1.73586118300774;
   fWeightMatrix1to2[5][8] = 0.854864287335035;
   fWeightMatrix1to2[6][8] = -2.32931387950697;
   fWeightMatrix1to2[7][8] = 0.0677493731318822;
   fWeightMatrix1to2[8][8] = -0.325424308099081;
   fWeightMatrix1to2[9][8] = -2.07776530907807;
   fWeightMatrix1to2[10][8] = 1.54106282269192;
   fWeightMatrix1to2[0][9] = 0.108639302535881;
   fWeightMatrix1to2[1][9] = 1.19541178220462;
   fWeightMatrix1to2[2][9] = 1.22030470103182;
   fWeightMatrix1to2[3][9] = 0.175158060471842;
   fWeightMatrix1to2[4][9] = 1.08248985919414;
   fWeightMatrix1to2[5][9] = -1.51214619356014;
   fWeightMatrix1to2[6][9] = -1.25111249851883;
   fWeightMatrix1to2[7][9] = -0.607143000575685;
   fWeightMatrix1to2[8][9] = -0.798680428930455;
   fWeightMatrix1to2[9][9] = -1.69956162014315;
   fWeightMatrix1to2[10][9] = -0.436039683170901;
   fWeightMatrix1to2[0][10] = 1.02038062300743;
   fWeightMatrix1to2[1][10] = -0.0874114651714851;
   fWeightMatrix1to2[2][10] = -1.9513630966022;
   fWeightMatrix1to2[3][10] = 1.38187868298096;
   fWeightMatrix1to2[4][10] = -1.59399543553275;
   fWeightMatrix1to2[5][10] = -0.66359326293901;
   fWeightMatrix1to2[6][10] = -1.23844253631972;
   fWeightMatrix1to2[7][10] = 0.423221849103614;
   fWeightMatrix1to2[8][10] = -0.245928643708205;
   fWeightMatrix1to2[9][10] = -0.230892445198297;
   fWeightMatrix1to2[10][10] = -0.767730918555554;
   fWeightMatrix1to2[0][11] = 0.919236340540877;
   fWeightMatrix1to2[1][11] = -0.181012807630265;
   fWeightMatrix1to2[2][11] = 0.73359701296864;
   fWeightMatrix1to2[3][11] = -1.28520151566973;
   fWeightMatrix1to2[4][11] = -0.529107755428057;
   fWeightMatrix1to2[5][11] = -1.61816966813308;
   fWeightMatrix1to2[6][11] = 0.857942955182592;
   fWeightMatrix1to2[7][11] = 0.932366702391555;
   fWeightMatrix1to2[8][11] = -0.0215924908216973;
   fWeightMatrix1to2[9][11] = 1.05555548833913;
   fWeightMatrix1to2[10][11] = 0.829107187626085;
   fWeightMatrix1to2[0][12] = -0.107281481126566;
   fWeightMatrix1to2[1][12] = 0.720913998431686;
   fWeightMatrix1to2[2][12] = -0.75016346021492;
   fWeightMatrix1to2[3][12] = -0.412157844683154;
   fWeightMatrix1to2[4][12] = 1.43423800590101;
   fWeightMatrix1to2[5][12] = 0.841197894984392;
   fWeightMatrix1to2[6][12] = -2.22033519047144;
   fWeightMatrix1to2[7][12] = -2.18346526138037;
   fWeightMatrix1to2[8][12] = 0.323067961383045;
   fWeightMatrix1to2[9][12] = -0.183165788868951;
   fWeightMatrix1to2[10][12] = 1.6369524561641;
   // weight matrix from layer 2 to 3
   fWeightMatrix2to3[0][0] = -0.621010055337354;
   fWeightMatrix2to3[0][1] = 0.317622869301767;
   fWeightMatrix2to3[0][2] = -0.71282110827552;
   fWeightMatrix2to3[0][3] = -0.153334496289368;
   fWeightMatrix2to3[0][4] = -0.416810972484272;
   fWeightMatrix2to3[0][5] = -1.13069444625229;
   fWeightMatrix2to3[0][6] = -1.29131606340091;
   fWeightMatrix2to3[0][7] = -0.38690707138915;
   fWeightMatrix2to3[0][8] = 1.10629872537339;
   fWeightMatrix2to3[0][9] = 1.33656812807077;
   fWeightMatrix2to3[0][10] = -0.7607902790011;
   fWeightMatrix2to3[0][11] = 0.924709720358759;
}

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
}