Algorithms

This is the module for basic ELM algorithms.

Neural Extreme Learning Machine

This is the implementation as a single hidden layer feedforward network (SLFN).

class algorithm.NELM

Bases: home.cperales.pruebas.Ridge-ELM-framework.generic.NMethod

Neural Extreme Learning Machine with a hidden layer

H = None

None

fit(trainData, trainTarg, parameters)
TrainData:Data matrix n x m, with n instances and m features.
TrainTarg:Target J-encoded matrix n x j.
Parameters:Structure with the cross validated hyperparameters.
get_indicator(testPatterns)

Get matrixes

trainPatterns = None

None

Kernel Extreme Learning Machine

This is the implementation using kernel trick, which is also known as Kernel Ridge Classification.

class algorithm.KELM

Bases: home.cperales.pruebas.Ridge-ELM-framework.generic.KMethod

Kernel Extreme Learning Machine

fit(trainData, trainTarg, parameters)
TrainData:Data matrix n x m, with n instances and m features.
TrainTarg:Target J-encoded matrix n x j.
Parameters:Structure with the cross validated hyperparameters.
get_indicator(testPatterns)
TestPattern:Data matrix n x m, with n instances to predict and m features.
trainPatterns = None

Train data is stored for kernel trick.