newff                 package:AMORE                 R Documentation

_F_e_e_d_f_o_r_w_a_r_d _N_e_u_r_a_l _N_e_t_w_o_r_k

_D_e_s_c_r_i_p_t_i_o_n:

     Creates a feedforward artificial neural network according to the
     structure established by the AMORE package standard.

_U_s_a_g_e:

     newff(n.inputs, n.hidden, n.outputs, learning.rate.global, momentum.global, error.criterium, Stao, hidden.layer, output.layer) 

_A_r_g_u_m_e_n_t_s:

n.inputs: Number of input neurons or predictors.

n.hidden: Number of hidden layer neurons.

n.outputs: Number of output layer neurons.

learning.rate.global: Learning rate.

momentum.global: Momentum (Set to 0 if you do not want to use it).

error.criterium: Criterium used to measure to proximity of the neural
          network prediction to its target. Currently we can choose
          amongst: 

             *  "MSE": Mean Squared Error

             *  "LMLS": Least Mean Logarithm Squared (Liano 1996).

             *  "TAO": TAO Error (Pernia, 2004).

    Stao: Stao parameter for the TAO error criterium. Unused by the
          rest of criteria.

hidden.layer: Activation function of the hidden layer neurons.
          Available functions are:

             *  "purelin".

             *  "tansig". 

             *  "sigmoid".

             *  "hardlim".

output.layer: Activation function of the hidden layer neurons according
          to the former list shown above.

_V_a_l_u_e:

     _newff_ returns a feedforward neural network object.

_A_u_t_h_o_r(_s):

     Manuel Castejn Limas.              manuel.castejon@unileon.es
      Joaquin Ordieres Mer.             
     joaquin.ordieres@dim.unirioja.es
      Ana Gonzlez Marcos.                ana.gonzalez@unileon.es 
      Alpha V. Perna Espinoza.           alpha.pernia@alum.unirioja.es
      Eliseo P. Vergara Gonzalez.        
     eliseo.vergara@dim.unirioja.es
      Francisco Javier Martinez de Pisn.
     francisco.martinez@dim.unirioja.es
      Fernando Alba Elas.                fernando.alba@unavarra.es

_R_e_f_e_r_e_n_c_e_s:

     Pernia Espinoza, A.V. TAO-robust backpropagation learning
     algorithm. Neural Networks. In press. 

      Simon Haykin. Neural Networks. A comprehensive foundation. 2nd
     Edition. 


_S_e_e _A_l_s_o:

     'init.neuron', 'random.init.NeuralNet', 'random.init.neuron',
     'select.activation.function' , 'init.neuron'

_E_x_a_m_p_l_e_s:

     #Example 1

     library(AMORE)
     # P is the input vector
     P <- matrix(sample(seq(-1,1,length=1000), 1000, replace=FALSE), ncol=1) 
     # The network will try to approximate the target P^2
     target <- P^2                                   
     #We create a feedforward network, with 2 neurons in the hidden layer. Tansig and Purelin activation functions.
     net <- newff(n.inputs=1,n.hidden=2,n.outputs=1,learning.rate.global=1e-1, momentum.global=0.5 , error.criterium="MSE", hidden.layer="tansig", output.layer="purelin")
     net <- train(net,P,target,n.epochs=100, g=adapt.NeuralNet,error.criterium="MSE", Stao=NA, report=TRUE, show.step=10 )

