Learn R Programming
⚠️There's a newer version (0.2-16) of this package.Take me there.

AMORE (version 0.1.1)

A MORE flexible neural network package

Description

This package was born to release the TAO robust neural network algorithm to the R users. It has grown and I think it can be of interest for the users wanting to implement their own training algorithms as well as for those others whose needs lye only in the "user space".

Copy Link

Version

Install

install.packages('AMORE')

Monthly Downloads

133

Version

0.1.1

License

GPL version 2 or newer.

Maintainer

Manuel Castejon Limas

Last Published

February 12th, 2020

Functions in AMORE (0.1.1)

forward.adapt.R.NeuralNet

Perform the forward pass in the adaptative training.
adapt

Adaptative on-line single pattern training
backpropagate.adapt.R.NeuralNet

Backpropagates the single pattern error modifying accordingly the Neural Network's weights and biases.
backpropagate.adapt.R.neuron

Backpropagates the single pattern error modifying accordingly the neuron's weights and bias.
restrict

Restrict the patterns to the [-1,1] interval.
forwardpass.R.NeuralNet

Simulate a Neural Network response.
error.TAO

Neural network training error criteria.
select.activation.function

Provides R code of the selected activation function.
set.learning.rate.and.momentum

Set Learning rate and momentum.
newff

Feedforward Neural Network
init.neuron

Neuron constructor.
train

Neural network training function.
forward.adapt.R.neuron

Perform the neuron forward pass in the adaptative training.
train.compare

Trains the same neural network according to different error criteria.
training.report

Neural network training report generator function.
sim.C.NeuralNet

Performs the simulation of a neural network providing the output values.
random.init.neuron

Initialize the neuron with random weigths and bias.
forwardpass.R.neuron

Simulate a neuron response.
random.init.NeuralNet

Initialize the network with random weigths and biases.