Gradient descent with momentum and adaptive learning rate backpropagation
net.trainFcn = 'traingdx'
[net,tr] = train(net,...)
traingdx is a network training function that
updates weight and bias values according to gradient descent momentum
and an adaptive learning rate.
net.trainFcn = 'traingdx' sets the network
[net,tr] = train(net,...) trains the network
Training occurs according to
parameters, shown here with their default values:
Maximum number of epochs to train
Ratio to increase learning rate
Ratio to decrease learning rate
Maximum validation failures
Maximum performance increase
Minimum performance gradient
Epochs between displays (
Generate command-line output
Show training GUI
Maximum time to train in seconds
You can create a standard network that uses
To prepare a custom network to be trained with
to desired values.
In either case, calling
train with the resulting
network trains the network with
help feedforwardnet and
cascadeforwardnet for examples.
traingdx combines adaptive learning
rate with momentum training. It is invoked in the same way as
except that it has the momentum coefficient
an additional training parameter.
traingdx 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
respect to the weight and bias variables
variable is adjusted according to gradient descent with momentum,
dX = mc*dXprev + lr*mc*dperf/dX
dXprev is the previous change to the
weight or bias.
For each epoch, if performance decreases toward the goal, then
the learning rate is increased by the factor
If performance increases by more than the factor
the learning rate is adjusted by the factor
the change that increased the performance is not made.
Training stops when any of these conditions occurs:
The maximum number of
The maximum amount of
time is exceeded.
Performance is minimized to the
The performance gradient falls below
Validation performance has increased more than
since the last time it decreased (when using validation).