Week 05 · overview
Week 5: Compression and Generative Models
Autoencoders learn an encoder, bottleneck representation, and decoder by minimizing reconstruction error. GANs train a generator and discriminator in an adversarial loop. Both can produce outputs; neither makes those outputs true, original, safe, or useful by default.
| Day | Role | Evidence |
|---|---|---|
| 1 | Lesson 1: Autoencoders | Trace encode → latent → decode → reconstruction loss |
| 2 | Lesson 2: GANs | Trace generator/discriminator objectives and instability |
| 3 | Investigation | Compare bottleneck capacity and generative claims |
| 4 | Lab | Measure deterministic reconstruction loss |
| 5 | Assessment + Reflection | Repair an output-quality overclaim |
Your Latent Reconstruction Record must include both bottleneck runs, exact per-pattern and total errors, decoder outputs, a corrected claim, and a limitation. The Lab uses four supplied binary patterns and contacts no service.
The complete pinned Microsoft repository, notebooks, images, assignments, and
credits remain in upstream/. Review the source record.
Chapter question
How does Compression and Generative Models 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.