Scilab Function
Last update : 13/3/2006
ANN_LMBR - Function to train a feed-forward artificial neural network with one hidden layer.
Calling Sequence
-
[W,OUT,RMSE,[SSE,GAMK,SSX]] = ANN_LMBR(IN,TARG,Nhid,Wini,[EPOCH,EpochShow,GraphFin,...])
Parameters
-
IN
: Input data (matrix [PxN] where P is the number of input neurons and N the number of input patterns)
-
TARG
: Target data (matrix [MxN] where M is the number of ouput neurons and N the number of input patterns)
-
Nhid
: Number of neurons in the hidden layer
-
Wini
: Initial 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)
-
EPOCH
: Number of epochs (should >2). Default = 30
-
EpochShow
: Periodicity of results display during network calibration. Default = 10
-
GraphFin
: Graphical display of calibration progresses (%T or %F). Default = %T
-
W
: Final weight and biais values (same matrix structure than Wini).
-
OUT
: Final network outputs (Matrix [MxN] where M is the number of ouput neurons and N the number of input patterns)
-
RMSE
: Root Mean square error of final output compared with target
-
SSE
: Serie of SSE value (1 value for each epoch)
-
GAMK
: Serie of GAMK value (1 value for each epoch)
-
SSX
: Serie of SSX value (1 value for each epoch)
Description
-
The activation function of the hidden layer is the hyperbolic tangent and the identity function for the output layer.
The objective function to be minimized is the Sum of Squared Errors (SSE).
The training algorithm is Levenberg-Marquadt algorithm with bayesian regulation.
Examples
// Calibration of a network with 6 input nodes, 4 nodes in the hidden layer and 1 output node
IN = rand(6,100);
TARG = rand(1,100);
Wini = rand(4,7,2);
[W,OUT,RMSE] = ANN_LMBR(IN,TARG,4,Wini);
See Also
ANN_CONV_W
,
ANN_JACOB
,
ANN_NORM
,
ANN_SIM
,
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 Function
ANN_CONV_W, ANN_JACOB