MLP with one hidden layer - HTML documentation under construction.

Inheritance:

Public Methods

	TwoLayerTest ()
	TwoLayerTest (unsigned nout, unsigned nhidden, unsigned nin, act_func fout=sigmoid, act_func fhid1=sigmoid)
virtual	~TwoLayerTest ()
inline unsigned	Nhidden1 () const
vect&	compute (vect& vinput)
void	init_weights_const (double x)
void	print_weights (void)

Protected Fields

unsigned

n_hidden1

Inherited from OneLayerTest:

Public Methods

void read_weights(istream& f)

unsigned test(TrainingSet& tset)

void print_errors()

inline unsigned read_num_errors() const

inline double read_perc_errors() const

Protected Fields

LayerNet layertest[MAXLAYERS]

unsigned num_errors

double perc_errors

Protected Methods

unsigned maxclass(vect& out, int dim)

Inherited from Network:

Public Fields

static const char* const NET_EXT

static const char* const NETCV_EXT

static const char* const ERR_EXT

static const char* const OUT_EXT

static const unsigned OUTPUT

static const unsigned HIDDEN1

static const unsigned HIDDEN2

static const char* const CV_SUFFIX

Public Methods

inline unsigned Nlayers() const

inline unsigned Ninput() const

inline unsigned Noutput() const

Protected Fields

unsigned n_layers

unsigned n_inputs

unsigned n_outputs

Documentation

Two-Layer Perceptron
It Implemets a MLP with one hidden layer only for testing: no learning is allowed

TwoLayerTest()

TwoLayerTest(unsigned nout, unsigned nhidden, unsigned nin, act_func fout=sigmoid, act_func fhid1=sigmoid)

virtual ~TwoLayerTest()

inline unsigned Nhidden1() const

vect& compute(vect& vinput)

void init_weights_const(double x)

void print_weights(void)

unsigned n_hidden1

Direct child classes:

ThreeLayerTest

Alphabetic index HTML hierarchy of classes or Java