hiddenlayer-class: Class 'hiddenlayer'

In mugiro/elm: Extreme Learning Machine for regression and classification

Description

A S4 class to encapsulate the parameters of the hidden layer in a SLFN

Usage

## S4 method for signature 'hiddenlayer'
add_neurons(object, ninputs, nn, act_fun, w_in, b)

## S4 method for signature 'hiddenlayer'
show(object)

## S4 method for signature 'hiddenlayer'
prune(object, n_sel)

Methods (by generic)

• add_neurons: add neurons of the same type of activation function

• show: show an object of class hiddenlayer

• prune: Remove neurons from the hiddenlayer given an index of neurons

Slots

act_fun

a factor, with the type of activation function used in each neurons. The levels of the factor are the different type of activation function combined, while the length of the factor equals to the number of neurons of the layer.

w_in

a matrix, with the input weights. In the case of "rbf" neurons, it stands for the centroids of each hidden neurons.

b

a vector, with the input bias. In the case of rbf neurons, it stands for the gamma values associated to each neuron.

mugiro/elm documentation built on May 23, 2019, 8:21 a.m.