Name

ANN_SIM — Function to simulate the outputs of a feed-forward artificial neural network with one hidden layer

Calling Sequence

[OUT,[IN_W,HID_OUT]] = ANN_SIM(IN,Nhid,Nout,W)

Parameters

IN

Input data (matrix [PxN] where P is the number of input neurons and N the number of input patterns)

Nhid

Number of neurons in the hidden layer

Nout

Number of neurons in the ouput layer

W

Weight and bias values (2 dimensions Matrix [max(Nhid,M) x max(P+1,Nhid+1) x 2]).

Wini(1:Nhid,1,1) are the bias for the hidden neurons

Wini(1:Nhid,2:P+1,1) are the weights for the hidden neurons (P weights for each hidden neuron)

Wini(1:M,1,2) are the bias for the ouput neurons

Wini(1:M,2:Nhid+1,2) are the weights for the ouput neurons (Nhid weights for each output neuron)

OUT

Network outputs (Matrix [NoutxN])

IN_W

Weighted input from the input layer (matrix [Nhid x N])

HID_OUT

Outputs from the hidden layer (matrix [Nhid x N])

Description

  • The activation function of the hidden layer is the hyperbolic tangent and the identity function for the output layer.

    Note : weighted output from the hidden layer is equal to HID_OUT because of the identity activation function

  • Add here a paragraph of the function description

Examples

   // Ouput from a network with 6 input nodes, 4 nodes in the hidden layer and 1 output node
   IN = rand(6,100);
   W  = rand(4,7,2);
   [OUT,IN_W,HID_OUT] = ANN_SIM(IN,4,1,W)   
  

See Also

ANN_CONV_W , ANN_JACOB , ANN_NORM , ANN_LMBR

Authors

Julien Lerat

CEMAGREF Antony, HBAN Unit, julien.lerat@cemagref.fr

Bibliography

MacKay, Neural Computation, vol. 4, no. 3, 1992, pp. 415-447.

Foresee and Hagan, Proceedings of the International Joint Conference on Neural Networks, June, 1997.

Used Functions

Add here the used function name and references