Main Content

traingdm

Gradient descent with momentum backpropagation

Syntax

net.trainFcn = 'traingdm'
[net,tr] = train(net,...)

Description

traingdm is a network training function that updates weight and bias values according to gradient descent with momentum.

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

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

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

net.trainParam.epochs1000

Maximum number of epochs to train

net.trainParam.goal0

Performance goal

net.trainParam.lr0.01

Learning rate

net.trainParam.max_fail6

Maximum validation failures

net.trainParam.mc0.9

Momentum constant

net.trainParam.min_grad1e-5

Minimum performance gradient

net.trainParam.show25

Epochs between showing progress

net.trainParam.showCommandLinefalse

Generate command-line output

net.trainParam.showWindowtrue

Show training GUI

net.trainParam.timeinf

Maximum time to train in seconds

Network Use

You can create a standard network that uses traingdm with feedforwardnet or cascadeforwardnet. To prepare a custom network to be trained with traingdm,

  1. Set net.trainFcn to 'traingdm'. This sets net.trainParam to traingdm’s default parameters.

  2. Set net.trainParam properties to desired values.

In either case, calling train with the resulting network trains the network with traingdm.

See help feedforwardnet and help cascadeforwardnet for examples.

More About

collapse all

Algorithms

traingdm 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 gradient descent with momentum,

dX = mc*dXprev + lr*(1-mc)*dperf/dX

where dXprev is the previous change to the weight or bias.

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).

Version History

Introduced before R2006a