Visibility: public Uploaded 05-04-2017 by Titus Kervezee Weka_3.8.1 1 runs
0 likes downloaded by 0 people 0 issues 0 downvotes , 0 total downloads
  • Verified_Supervised_Classification weka weka_3.8.1
Issue #Downvotes for this reason By

Loading wiki
Help us complete this description Edit
Weka implementation of SGD


-do-not-check-capabilitiesIf set, classifier capabilities are not checked before classifier is built (use with caution).
CThe epsilon threshold (epsilon-insenstive and Huber loss only, default = 1e-3)default: 0.001
EThe number of epochs to perform (batch learning only, default = 500)default: 500
FSet the loss function to minimize. 0 = hinge loss (SVM), 1 = log loss (logistic regression), 2 = squared loss (regression), 3 = epsilon insensitive loss (regression), 4 = Huber loss (regression). (default = 0)default: 0
LThe learning rate. If normalization is turned off (as it is automatically for streaming data), then the default learning rate will need to be reduced (try 0.0001). (default = 0.01).default: 0.01
MDon't replace missing values
NDon't normalize the data
RThe lambda regularization constant (default = 0.0001)default: 1.0E-4
SRandom number seed. (default 1)default: 1
batch-sizeThe desired batch size for batch prediction (default 100).
num-decimal-placesThe number of decimal places for the output of numbers in the model (default 2).
output-debug-infoIf set, classifier is run in debug mode and may output additional info to the console


List all runs
Rendering chart
Rendering table