Embeddings and Tokenisation

August 30, 2024 · 155 words · One minute · events

Demystify AI’s Text Understanding: A Hands-on Journey into Embeddings & Tokenization

Ever wondered how ChatGPT turns your words into meaningful responses? Or how Spotify knows which songs you’ll love? The secret lies in embeddings and tokenization - and this workshop will show you exactly how they work.

Prerequisites

  • Basic Python programming knowledge
  • Familiarity with simple data structures (lists, dictionaries)
  • No advanced math required - we’ll build intuition first!

What You’ll Learn

  • Turn text into numbers that AI models can understand
  • Visualize word embeddings and understand semantic relationships
  • Learn how tokenization is done, and a brief primer on positional embeddings
  • Understand the math behind tokenisation and embeddings.

By Workshop’s End

You’ll gain the ability to:

  • Understand how modern AI models process text at a fundamental level
  • Get an understanding of different embedding techniques
  • Brief taster to next lesson’s topic: Transformers

Ready to peek under the hood of AI language understanding? Start your journey here: Workshop Link