Commit 3cbcd5be authored by Jussi Lindgren's avatar Jussi Lindgren

Documentation: Updated docs for the Classifier Trainer and Processor boxes

parent 3e48b547
......@@ -33,6 +33,12 @@ This input should be connected to the feature vector stream to classify. Each ti
a classification process will be triggered. Consequently, a classification stimulation will be sent on the
first output of this box.
* |OVP_DocEnd_BoxAlgorithm_ClassifierProcessor_Input1|
* |OVP_DocBegin_BoxAlgorithm_ClassifierProcessor_Input2|
If this input receives the stimulation OVTK_StimulationId_TrainCompleted, the box will reload the classifier
from the disk. It can be used to implement simple incremental learning.
* |OVP_DocEnd_BoxAlgorithm_ClassifierProcessor_Input2|
__________________________________________________________________
Outputs description
......
......@@ -72,7 +72,7 @@ parameters you will have available. This will depend on the classification algor
* |OVP_DocEnd_BoxAlgorithm_ClassifierTrainer_Settings|
*
* * |OVP_DocBegin_BoxAlgorithm_ClassifierTrainer_Setting1|
This is the stimulation to consider to trigger the training process.
This is the stimulation to consider to trigger the training process and save the learned classifier to disk.
* |OVP_DocEnd_BoxAlgorithm_ClassifierTrainer_Setting1|
*
* * |OVP_DocBegin_BoxAlgorithm_ClassifierTrainer_Setting2|
......@@ -111,8 +111,14 @@ the classifier trained with the whole data. The cross-validation is only an erro
the resulting model. See the miscellaneous section for details on how the k-fold test is done in this box, and possible
caveats about the cross-validation procedure.
* |OVP_DocEnd_BoxAlgorithm_ClassifierTrainer_Setting10|
* |OVP_DocBegin_BoxAlgorithm_ClassifierTrainer_Setting11|
If the number of class labels is unbalanced, the classifiers tend to be biased towards the majority labels.
This option can be used to resample the dataset to feature all classes equally. Doing this may make sense
if the box is used for incremental learning, where all classes may not be equally represented in the training data
obtained so far, even if the design itself is balanced. Note that enabling this will make the cross-validation
results optimistic. In most conditions, the feature should be disabled.
* |OVP_DocBegin_BoxAlgorithm_ClassifierTrainer_Setting11|
__________________________________________________________________
......@@ -258,5 +264,13 @@ source, the signal processing chains for the different classes, or the classifie
then to be investigated. Also, if very low accuracies are observed in these matrices, it may give reason
to suspect that prediction accuracies on fresh data might be likewise lacking -- or worse.
Incremental Learning
The box can also be used for simple incremental (online) learning. To achieve this, simply send the box the training
stimulation and it will train a classifier with all the data it has received so far. You can give it more
feature vectors later, and trigger the learning again by sending another stimulation. Likewise, the corresponding
classifier processor box can be made to load new classifiers during playback. With classifiers like LDA,
this practice is usually feasible when the data is reasonable sized (as in basic motor imagery).
* |OVP_DocEnd_BoxAlgorithm_ClassifierTrainer_Miscellaneous|
*/
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment