Text, Tokenization, and Embeddings

introduce text workflows without jumping straight to large language models.

Units

1. Unit 09.00: 09.00 Text as data and why tokenization matters
2. Unit 09.01: 09.01 Vocabulary, sequence length, padding, and truncation
3. Unit 09.02: 09.02 TextVectorization and simple baselines
4. Unit 09.03: 09.03 Embedding layers and learned representations
5. Unit 09.04: 09.04 Comparing text representations honestly
6. Unit 09.05: 09.05 Project step: text classification or embedding report

Module work

• Activity
• Knowledge check
• Summary