Posts in tag
effortpost
trees are harlequins, words are harlequins — the transformer … “explained”?
Okay, here’s my promised post on the Transformer architecture. (Tagging @sinesalvatorem as requested) The Transformer architecture is the hot new thing in machine learning, especially in NLP. In the course of roughly a year, the Transformer has given us things like: GPT-2, everyone’s new favorite writer-bot, with whose work I am sure you are familiar …