Learn R Programming

CaDENCE (version 1.2.5)

Conditional Density Estimation Network Construction and Evaluation

Description

Parameters of a user-specified probability distribution are modelled by a multi-layer perceptron artificial neural network. This framework can be used to implement probabilistic nonlinear models including mixture density networks, heteroscedastic regression models, zero-inflated models, etc. following Cannon (2012) .

Copy Link

Version

Install

install.packages('CaDENCE')

Monthly Downloads

256

Version

1.2.5

License

GPL-2

Maintainer

Alex Cannon

Last Published

December 5th, 2017

Functions in CaDENCE (1.2.5)

CaDENCE-package

Conditional Density Estimation Network Construction and Evaluation (CaDENCE)
FraserSediment

Sediment and stream discharge data for Fraser River at Hope
gam.style

GAM-style effects plots for interpreting CDEN models
bweibull

Bernoulli-Weibull distribution
logistic

Logistic sigmoid function
cadence.cost

Cost function for CDEN model fitting
rprop

Resilient backpropagation (Rprop) optimization algorithm
cadence.fit

Fit a CDEN model
xval.buffer

Cross-validation indices with a buffer between training/validation datasets
pareto2

Pareto 2 (Lomax) and Bernoulli-Pareto 2 distributions
cadence.predict

Predict conditional distribution parameters from a fitted CDEN model
rbf

Radial basis function kernel
dummy.code

Convert a factor to a matrix of dummy codes
bgamma

Bernoulli-gamma distribution
blnorm

Bernoulli-lognormal distribution
cadence.initialize

Initialize a CDEN weight vector