Description Usage Arguments Details Value See Also Examples
View source: R/minimizeClassifier.R
This function trains a DArch
classifier network with the
conjugate gradient method.
1 2 3 4 5 6 7 | minimizeClassifier(darch, trainData, targetData,
cg.length = getParameter(".cg.length"),
cg.switchLayers = getParameter(".cg.length"),
dropout = getParameter(".darch.dropout"),
dropConnect = getParameter(".darch.dropout.dropConnect"),
matMult = getParameter(".matMult"), debugMode = getParameter(".debug"),
...)
|
darch |
A instance of the class |
trainData |
The training data matrix. |
targetData |
The labels for the training data. |
cg.length |
Numbers of line search |
cg.switchLayers |
Indicates when to train the full network instead of only the upper two layers |
dropout |
See |
dropConnect |
See |
matMult |
Matrix multiplication function, internal parameter. |
debugMode |
Whether debug mode is enabled, internal parameter. |
... |
Further parameters. |
This function is build on the basis of the code from G. Hinton et. al.
(http://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html - last visit
2016-04-30) for the fine tuning of deep belief nets. The original code is
located in the files 'backpropclassify.m', 'CG_MNIST.m' and
'CG_CLASSIFY_INIT.m'.
It implements the fine tuning for a classification net with backpropagation
using a direct translation of the minimize
function from C.
Rassmussen (available at http://www.gatsby.ucl.ac.uk/~edward/code/minimize/
- last visit 2016-04-30) to R.
The parameter cg.switchLayers
is for the switch between two training
type. Like in the original code, the top two layers can be trained alone
until epoch
is equal to epochSwitch
. Afterwards the entire
network will be trained.
minimizeClassifier
supports dropout but does not use the weight
update function as defined via the darch.weightUpdateFunction
parameter of darch
, so that weight decay, momentum etc. are not
supported.
The trained DArch
object.
Other fine-tuning functions: backpropagation
,
minimizeAutoencoder
,
rpropagation
1 2 3 4 5 6 7 8 9 |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.