Main Content

trainrp

Resilient backpropagation

Description

net.trainFcn = 'trainrp' sets the network trainFcn property.

[trainedNet,tr] = train(net,...) trains the network with trainrp.

trainrp is a network training function that updates weight and bias values according to the resilient backpropagation algorithm (Rprop).

Training occurs according to trainrp training parameters, shown here with their default values:

  • net.trainParam.epochs — Maximum number of epochs to train. The default value is 1000.

  • net.trainParam.show — Epochs between displays (NaN for no displays). The default value is 25.

  • net.trainParam.showCommandLine — Generate command-line output. The default value is false.

  • net.trainParam.showWindow — Show training GUI. The default value is true.

  • net.trainParam.goal — Performance goal. The default value is 0.

  • net.trainParam.time — Maximum time to train in seconds. The default value is inf.

  • net.trainParam.min_grad — Minimum performance gradient. The default value is 1e-5.

  • net.trainParam.max_fail — Maximum validation failures. The default value is 6.

  • net.trainParam.lr — Learning rate. The default value is 0.01.

  • net.trainParam.delt_inc — Increment to weight change. The default value is 1.2.

  • net.trainParam.delt_dec — Decrement to weight change. The default value is 0.5.

  • net.trainParam.delta0 — Initial weight change. The default value is 0.07.

  • net.trainParam.deltamax — Maximum weight change. The default value is 50.0.

example

Examples

collapse all

This example shows how to train a feedforward network with a trainrp training function to solve a problem with inputs p and targets t.

Create the inputs p and the targets t that you want to solve with a network.

p = [0 1 2 3 4 5];
t = [0 0 0 1 1 1];

Create a two-layer feedforward network with two hidden neurons and this training function.

net = feedforwardnet(2,'trainrp');

Train and test the network.

net.trainParam.epochs = 50;
net.trainParam.show = 10;
net.trainParam.goal = 0.1;
net = train(net,p,t);
a = net(p)

For more examples, see help feedforwardnet and help cascadeforwardnet.

Input Arguments

collapse all

Input network, specified as a network object. To create a network object, use for example, feedforwardnet or narxnet.

Output Arguments

collapse all

Trained network, returned as a network object.

Training record (epoch and perf), returned as a structure whose fields depend on the network training function (net.NET.trainFcn). It can include fields such as:

  • Training, data division, and performance functions and parameters

  • Data division indices for training, validation and test sets

  • Data division masks for training validation and test sets

  • Number of epochs (num_epochs) and the best epoch (best_epoch).

  • A list of training state names (states).

  • Fields for each state name recording its value throughout training

  • Performances of the best network (best_perf, best_vperf, best_tperf)

More About

collapse all

Algorithms

trainrp can train any network as long as its weight, net input, and transfer functions have derivative functions.

Backpropagation is used to calculate derivatives of performance perf with respect to the weight and bias variables X. Each variable is adjusted according to the following:

dX = deltaX.*sign(gX);

where the elements of deltaX are all initialized to delta0, and gX is the gradient. At each iteration the elements of deltaX are modified. If an element of gX changes sign from one iteration to the next, then the corresponding element of deltaX is decreased by delta_dec. If an element of gX maintains the same sign from one iteration to the next, then the corresponding element of deltaX is increased by delta_inc. See Riedmiller, M., and H. Braun, “A direct adaptive method for faster backpropagation learning: The RPROP algorithm,” Proceedings of the IEEE International Conference on Neural Networks,1993, pp. 586–591.

Training stops when any of these conditions occurs:

  • The maximum number of epochs (repetitions) is reached.

  • The maximum amount of time is exceeded.

  • Performance is minimized to the goal.

  • The performance gradient falls below min_grad.

  • Validation performance (validation error) has increased more than max_fail times since the last time it decreased (when using validation).

References

[1] Riedmiller, M., and H. Braun, “A direct adaptive method for faster backpropagation learning: The RPROP algorithm,” Proceedings of the IEEE International Conference on Neural Networks,1993, pp. 586–591.

Version History

Introduced before R2006a