<< ann_FFBP_gdx Neural_Network_Functions ann_FFBP_run >>

NeuralNet >> Neural_Network_Functions > ann_FFBP_lm

ann_FFBP_lm

ANN FeedForward Backpropagation Levenberg–Marquardt algorithm training function

Calling Sequence

W = ann_FFBP_lm(P,T,N)
W = ann_FFBP_lm(P,T,N,af,mu,mumax,theta,itermax,mse_min,gd_min)

Parameters

P :

Training input

T :

Training target

N :

Number of Neurons in each layer, incluing Input and output layer

af :

Activation Function from 1st hidden layer to the output layer

mu :

lm mu value

mumax :

Maximum allowed mu value

theta :

mu mutiplier

itermax :

Maximum iteration

mse_min :

Minumum Error (Performance Goal)

gd_min :

Minimum Gradient

W :

Output Weight and bias

Description

This function perform FeedForward Backpropagation with Levenberg–Marquardt algorithm training function.

Examples

P = [1 2 3 4; 1 2 3 4];
T = [1 2 3 4];
W = ann_FFBP_lm(P,T,[2 3 1]);
y = ann_FFBP_run(P,W)

See also

Authors


Report an issue
<< ann_FFBP_gdx Neural_Network_Functions ann_FFBP_run >>