From e8bf12818679914ecca8cbf5b14509c1f55e9d4f Mon Sep 17 00:00:00 2001 From: "Feng, Xixuan (Aaron)" Date: Fri, 7 Mar 2014 14:26:46 -0800 Subject: [PATCH] Doc: Add constant column for LSVM normalization Pivotal Tracker: #62182584 --- methods/kernel_machines/src/pg_gp/online_sv.sql_in | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/methods/kernel_machines/src/pg_gp/online_sv.sql_in b/methods/kernel_machines/src/pg_gp/online_sv.sql_in index 601352761..0c9c6f232 100644 --- a/methods/kernel_machines/src/pg_gp/online_sv.sql_in +++ b/methods/kernel_machines/src/pg_gp/online_sv.sql_in @@ -144,7 +144,8 @@ lsvm_classification( input_table, Note that, as any gradient descent methods, IGD will converge with a greater eta (stepsize), thus faster, if the input training data is well-conditioned. We highly recommend user to perform data preparation, such that the mean value -of each feature column is 0 and standard error is 1. We plan to provide a +of each feature column is 0 and standard error is 1, and append an extra +feature with constant value 1 for intercept term. We plan to provide a function for this when this module graduates from early stage development. - Learn linear or non-linear SVM(s) using the method described in [1].