Neural Network Toolbox |
Gradient descent backpropagation
Syntax
[net,TR,Ac,El] = traingd(net,Pd,Tl,Ai,Q,TS,VV,TV)
Description
traingd
is a network training function that updates weight and bias values according to gradient descent.
traingd(net,Pd,Tl,Ai,Q,TS,VV)
takes these inputs,
Ai
-- Initial input delay conditions.
VV
-- Either an empty matrix []
or a structure of validation vectors.
TR
-- Training record of various values over each epoch:
Training occurs according to the traingd
's training parameters shown here with their default values:
net.trainParam.epochs 10
Maximum number of epochs to train
net.trainParam.goal 0
Performance goal
net.trainParam.lr 0.01
Learning rate
net.trainParam.max_fail 5
Maximum validation failures
net.trainParam.min_grad 1e-10
Minimum performance gradient
Dimensions for these variables are
Pd
-- No
x Ni
x TS
cell array, each element P{i,j,ts}
is a Dij
x Q
matrix.
Tl
-- Nl
x TS
cell array, each element P{i,ts}
is an Vi
x Q
matrix.
Ai
-- Nl
x LD
cell array, each element Ai{i,k}
is an Si
x Q
matrix.
If VV
or TV
is not []
, it must be a structure of validation vectors,
VV.PD, TV.PD
-- Validation/test delayed inputs.
VV.Tl, TV.Tl
-- Validation/test layer targets.
VV.Ai, TV.Ai
-- Validation/test initial input conditions.
Validation vectors are used to stop training early if the network performance on the validation vectors fails to improve or remains
the same for
max_fail
epochs in a row. Test vectors are used as a further check that the network is generalizing well, but do not
have any effect on training.
traingd(code)
returns useful information for each code
string:
Network Use
You can create a standard network that uses traingd
with newff
, newcf
, or newelm
.
To prepare a custom network to be trained with traingd
:
net.trainFcn
to 'traingd
'. This will set net.trainParam
to traingd
's default parameters.
net.trainParam
properties to desired values.
In either case, calling train
with the resulting network will train the network with traingd
.
See newff
, newcf
, and newelm
for examples.
Algorithm
traingd
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:
Training stops when any of these conditions occur:
epochs
(repetitions) is reached.
time
has been exceeded.
goal
.
mingrad
.
max_fail
times since the last time it decreased (when using validation).
See Also
newff
,
newcf
,
traingdm
,
traingda
,
traingdx
,
trainlm
traincgp | traingda |
© 1994-2005 The MathWorks, Inc.