Continuing from the recent introduction to bijectors in TensorFlow Probability (TFP), this post brings autoregressivity to the table. Using TFP through the new R package tfprobability, we look at the implementation of masked autoregressive flows (MAF) and put them to use on two different datasets.
With the rapid advance in NLP models we have outpaced out ability to measure just how good they are at human level language tasks. We need better NLP datasets now more than ever to both evaluate how good these models are and to be able to tweak them for out own business domains.
We will cover often-overlooked concepts vital to NLP, such as Byte Pair Encoding, and discuss how understanding them leads to better models.
Machine learning advancements lead to new ways to train models, as well as deceive them. This article discusses ways to train and defend against attacks.
Background & State of the Art
This article discusses GPT-2 and BERT models, as well using knowledge distillation to create highly accurate models with fewer parameters than their teachers
