759: Full Encoder-Decoder Transformers Fully Explained, with Kirill Eremenko
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Exploration of Transformers, Language Models, and Outputting Pixels vs. Words
This chapter dissects the linear transform layer in transformers, their language capabilities, and the possibility of generating image pixels with transformers. It also delves into outputting classes instead of words, with examples from models like BERT and the importance of a CLS token in such frameworks.
Transcript
Play full episode
