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.

DayRoleEvidence
1Lesson 1: Text as tensorsTrace tokens, vocabulary, one-hot, bag-of-words, and sequences
2Lesson 2: EmbeddingsExplain dense learned vectors and context-based training
3InvestigationCalculate similarity and expose representation dependence
4LabCompare one-hot and dense token vectors
5Assessment + ReflectionRepair 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.