Machine Learning
Milestone 4 of 7 · industry roleplay

A deep-learning project, safely

Triage patient messages with a transformer and route scanned documents with a CNN: choose models against real constraints, label data, diagnose training, and never miss an urgent message. Includes 4 hands-on Python coding tasks (pandas, scikit-learn), checked by automated tests.

Rigour50Communication50Ethics50Impact50Teamwork50
Mon 9:00A new projectMon 10:30"How long will it take?"Tue 10:00Label the training dataTue 11:30Code it: Cohen's kappaWed 10:00Pick the text modelWed 11:00Code it: the text baselineWed 15:00Training is acting upWed 16:30Code it: a neural network with early stoppingThu 9:00Scanned documentsThu 11:00Never miss an urgent messageThu 12:00Code it: a threshold that guarantees recallThu 17:30Ship it Friday?Fri 16:00Take-home: train it for real
Mon 9:00A new projectMeeting room
Maya
Tomás
Leah
Maya ChenProduct Manager
Riv

Bluegum Health, Riverside Clinics and every person here are fictional. The decisions, tools and practices are modelled on how real ML teams work.

Ready