Variational Autoencoder Models for IRT Parameter Estimation
Build the encoder for a VAE
Build a VAE that fits to a normal, full covariance N(m,S) latent distr...
Build a VAE that fits to a standard N(0,I) latent distribution with in...
Display a message upon loading package
Feed forward response sets through the encoder, which outputs student ...
Get trainable variables from the decoder, which serve as item paramete...
ML2Pvae: A package for creating a VAE whose decoder recovers the param...
A custom kernel constraint function that forces nonzero weights to be ...
A custom kernel constraint function that restricts weights between the...
A reparameterization in order to sample from the learned multivariate ...
A reparameterization in order to sample from the learned standard norm...
Trains a VAE or autoencoder model. This acts as a wrapper for keras::f...
A custom loss function for a VAE learning a multivariate normal distri...
A custom loss function for a VAE learning a standard normal distributi...
Give error messages for invalid inputs in exported functions.
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.