Package: ML2Pvae
Type: Package
Title: Variational Autoencoder Models for IRT Parameter Estimation
Version: 1.0.0.1
Authors@R: c(
    person("Geoffrey", "Converse", email = "converseg@gmail.com", role = c("aut", "cre", "cph")),
    person("Suely", "Oliveira", email = "suely-oliveira@uiowa.edu", role = c("ctb", "ths")),
    person("Mariana", "Curi", email = "mcuri@icmc.usp.br", role = c("ctb"))
    )
Maintainer: Geoffrey Converse <converseg@gmail.com>
Description: Based on the work of Curi, Converse, Hajewski, and Oliveira (2019) <doi:10.1109/IJCNN.2019.8852333>. This package provides easy-to-use functions which create a variational autoencoder (VAE) to be used for parameter estimation in Item Response Theory (IRT) - namely the Multidimensional Logistic 2-Parameter (ML2P) model. To use a neural network as such, nontrivial modifications to the architecture must be made, such as restricting the nonzero weights in the decoder according to some binary matrix Q. The functions in this package allow for straight-forward construction, training, and evaluation so that minimal knowledge of 'tensorflow' or 'keras' is required. 
Note: The developer version of 'keras' should be used, rather than the
        CRAN version. The latter will cause tests to fail on an initial
        run, but work on subsequent tries. To avoid this, use
        devtools::install_github("rstudio/keras"). The user also must
        have an installation of 'Python 3'.
License: MIT + file LICENSE
Encoding: UTF-8
LazyData: true
Imports: keras (>= 2.3.0), reticulate (>= 1.0), tensorflow (>= 2.2.0),
        tfprobability (>= 0.11.0)
RoxygenNote: 7.1.1
Suggests: knitr, rmarkdown, testthat, R.rsp
VignetteBuilder: R.rsp
Depends: R (>= 3.6)
URL: https://converseg.github.io
SystemRequirements: TensorFlow (https://www.tensorflow.org), Keras
        (https://keras.io), TensorFlow Probability
        (https://www.tensorflow.org/probability)
Config/reticulate: list( packages = list( list(package = "keras", pip =
        TRUE), list(package = "tensorflow", pip = TRUE), list(package =
        "tensorflow-probability", pip = TRUE) ) )
NeedsCompilation: no
Packaged: 2022-05-23 07:38:42 UTC; hornik
Author: Geoffrey Converse [aut, cre, cph],
  Suely Oliveira [ctb, ths],
  Mariana Curi [ctb]
Repository: CRAN
Date/Publication: 2022-05-23 08:02:16 UTC
Built: R 4.6.0; ; 2025-10-14 03:04:32 UTC; windows
