| Neural Network Toolbox | Search Help Desk |
| newfftd | Examples See Also |
Create a feed-forward input-delay backprop network
net = newfftd(PR,ID,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF)
newfftd(PR,ID,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF) takes,
PR - R x 2 matrix of min and max values for R input elements.
Si - Size of ith layer, for Nl layers.
TFi - Transfer function of ith layer, default = 'tansig'.
BTF - Backprop network training function, default = 'traingdx'.
BLF - Backprop weight/bias learning function, default = 'learngdm'.
PF - Performance function, default = 'mse'.
N layer feed-forward backprop network.
The transfer functions TFi can be any differentiable transfer function such as tansig, logsig, or purelin.
The training function BTF can be any of the backprop training functions such as trainlm, trainbfg, trainrp, traingd, etc.
WARNING: trainlm is the default training function because it is very fast, but it requires a lot of memory to run. If you get an "out-of-memory" error when training try doing one of these:
net.trainParam.mem_reduc to 2 or more. (See trainlm.)
trainbfg, which is slower but more memory-efficient than trainlm.
trainrp which is slower but more memory-efficient than trainbfg.
BLF can be either of the backpropagation learning functions such as learngd, or learngdm.
The performance function can be any of the differentiable performance functions such as mse or msereg.
Here is a problem consisting of an input sequence P and target sequence T that can be solved by a network with one delay.
P = {1 0 0 1 1 0 1 0 0 0 0 1 1 0 0 1};
T = {1 -1 0 1 0 -1 1 -1 0 0 0 1 0 -1 0 1};
Here a two-layer feed-forward network is created with input delays of 0 and 1. The network's input ranges from [0 to 1]. The first layer has five tansig neurons, the second layer has one purelin neuron. The trainlm network training function is to be used.
net = newfftd([0 1],[0 1],[5 1],{'tansig' 'purelin'});
Here the network is simulated.
Y = sim(net,P)Here the network is trained for 50 epochs. Again the network's output is calculated.
net.trainParam.epochs = 50; net = train(net,P,T); Y = sim(net,P)Feed-forward networks consist of
Nl layers using the dotprod weight function, netsum net input function, and the specified transfer functions.
The first layer has weights coming from the input with the specified input delays. Each subsequent layer has a weight coming from the previous layer. All layers have biases. The last layer is the network output.
Each layer's weights and biases are initialized with initnw.
Adaption is done with adaptwb which updates weights with the specified learning function. Training is done with the specified training function. Performance is measured according to the specified performance function.
newcf, newelm, sim, init, adapt, train