Module 8 · Neural and language models
Teach and adapt Module 8
Link the entry page as additional reading/practice. Its reading-site route is /lessons/08-neural-networks/ relative to the served site base. For a repository link, select a tested commit or release.
Facilitation and access
Use the same outcomes and written evidence for in-person/asynchronous learners. Begin with the foundation bridge, predict-before-run questions, and the shared script/notebook. Discussion has a solo equivalent. Optional depth is skippable, and GenAI is not required.
Interpretation can use named values and exact tables; code/artefacts demonstrate execution or authoring when those are assessed. A screenshot cannot substitute for an explanation, and a script does not prove notebook-interface operation. Verify the learner's actual assistive-technology route and provide private help.
Adaptation decisions
For IT telemetry, preserve host/time boundaries and final-test discipline before replacing numeric inputs. More layers do not replace data-quality or availability checks.
When changing a dataset, define its license/provenance, observation unit, target if any, availability, split, and limits first. Update preprocessing, inference contracts, examples, feedback, and tests together. Preserve the original source and disclose transformations. Do not label a tiny mechanics check as a credible production evaluation.
Outcome/evidence alignment
- M08.1: Explain input, hidden activation, output probability, loss, and gradient updates.
- M08.2: Fit training-only numeric preprocessing and a TensorFlow network.
- M08.3: Select a checkpoint using validation loss without fitting to final labels.
- M08.4: Compare held-out errors with a logistic baseline.
- M08.5: Save/reload a trained model and document compute and limitations.
Course alignment opportunities: CLO2, CLO4, CLO8. Advisory computing-outcome opportunities from the planning register: A1, A2, A3. These are opportunities for evidence, not proof of master's-level attainment or accreditation compliance. The original-module crosswalk remains in the previously prepared planning resources. Confirm adopted program criteria before formal use.
Verification limits
Actual framework training/inference, the public script, and notebook are exercised in the Linux CPU job. Windows/macOS framework execution is not inferred from that run. Exact counts/results are in the verified results table and commit-specific CI. Consult the accessibility evidence log for human interface-review coverage. Public feedback is for self-study; local grading/AI-use rules remain the adopting instructor's responsibility.
Teaching prototype: explanation, practice and feedback
This module now has an intermediate concepts page and three independently completed functions. Use the pilot protocol to observe understanding and support needs. Map learner artifacts with the practice evidence table. Visible code checks and solution execution are technical evidence; review the learner's reasoning and transfer separately. Preserve the existing outcomes and official assessment rules.