759: Full Encoder-Decoder Transformers Fully Explained, with Kirill Eremenko
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Understanding Full Encoder-Decoder Transformers for Translation Tasks
The chapter provides a detailed explanation of full encoder-decoder transformers used for translation tasks, breaking down the process into encoder and decoder components. It explains how English words are transformed into context-rich vectors in the encoder and how the decoder generates the translation word by word based on probabilities. The chapter also explores the concept of cross-attention between English and Spanish vectors to enhance the translation process.
Transcript
Play full episode
