Deep Learning
Milestone 4 of 4 · Deep Learning season · The Applied AI team

Small, fast and safe

Riverside wants the message-triage transformer on its own servers, with no GPU. Review the attention code, check how far pretrained features go with few labels, quantise the model, and decide how to ship it without missing an urgent message. Includes 4 hands-on Python coding tasks (NumPy, scikit-learn), checked by automated tests.

Rigour50Communication50Ethics50Impact50Teamwork50
Mon 9:00Small, fast and safeMon 11:00Code it: attention with masks and headsMon 15:00Code it: a whole transformer blockTue 9:30Few labels, big model?Tue 11:00Code it: few labels, pretrained featuresWed 10:00Code it: quantise a model to int8Thu 14:00Ship it to the clinic servers
Mon 9:00Small, fast and safeVideo call · Riverside IT
Priya
Maya
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