KNFST Learner

Calculates a Kernel Null Foley-Sammon Transformation that can be used to calculate a novelty score for a test sample in relation to the training samples.

The corresponding source code is a java adaption of the Matlab code provided by Bodesheim et al. for their paper "Kernel Null Space Methods for Novelty Detection".

Options

Training Columns

The columns which should be used for training (right now only numeric columns can be used for training)

Class Column

The column containing the class of the training samples

Kernel

Choose the Kernel that should be used

RBF - Radial basis function kernel (with parameter sigma)
HIK - Histogram intersection kernel
EXPHIK - Exponential variant of the HIK
Polynomial - Polynomial kernel (with parameters gamma, bias and sigma)

Sort Table

If you check this option, the input table will be sorted by class prior to calculating the nullspace. If it already is sorted by class, don't use this option.

Input Ports

: Training data

Output Ports

: Target points. Each class of the input table is represented by one point in the nullspace to which all instances of that class are projected.
: KNFST-model that can be used by a KNFST Novelty Scorer node to rate the novelty of instances

Popular Predecessors

Popular Successors

Views

This node has no views

Workflows

No workflows found

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.

Installation

To use this node in KNIME, install the extension KNIME Active Learning from the below update site following our NodePit Product and Node Installation Guide:

v5.3

A zipped version of the software site can be downloaded here.

Plugin provider: KNIME AG, Zurich, Switzerland

Plugin version: 5.3.0.v202312081533

On NodePit since: 2024-07-09

Last update: 2024-11-15

KNIME versions: Since v5.2

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!