Implementation of GLAD model from "Whose Vote Should Count More: Optimal Integration of Labels from Labelers of Unknown Expertise".

Work in progress:

• Check support for multi-class datasets.
• Add support for lazy datasets and mini-batch learning.
• Add support for prior distributions for $\alpha$ and $\beta$.
• Add optional learning of $p(z)$.
• Recreate results on simulated datasets from the paper.