Week 07 · overview
Week 7: Text Representations and Embeddings
Text must become numeric representations before a neural network can process it. Tokenization chooses units, vocabulary assigns identifiers, and vector representations determine which relationships a model can measure.
| Day | Role | Evidence |
|---|---|---|
| 1 | Lesson 1: Text as tensors | Trace tokens, vocabulary, one-hot, bag-of-words, and sequences |
| 2 | Lesson 2: Embeddings | Explain dense learned vectors and context-based training |
| 3 | Investigation | Calculate similarity and expose representation dependence |
| 4 | Lab | Compare one-hot and dense token vectors |
| 5 | Assessment + Reflection | Repair a vectors-prove-meaning claim |
Your Embedding Similarity Record preserves tokens, both representations, dot products, norms, cosine values, claim repair, and limitation. The Lab uses invented teaching vectors and contacts no embedding service.
The complete pinned Microsoft source and credits remain in upstream/.
Review the source record.
Chapter question
How does Text Representations and Embeddings change what evidence a student should trust?
What you will understand
You will connect the named mechanism to the evidence it can and cannot support.
What you will do
You will inspect supplied cases, trace the important calculation, and test one bounded claim.
What you will produce
You will produce the week evidence record named in the Lab or reflection.
How the week connects
This week carries the previous AI mechanism forward into a stricter evidence check.
Key vocabulary
mechanism; evidence; boundary; test; claim
Approximate time
Five class meetings at about 210 instructional minutes total.
Final evidence required
Submit the completed week record with at least two exact labels from the artifact.