Final project: defend an end-to-end AI system design
A turbine technician needs exact torque values from a 32,000-token manual, offline, on a 16 GB laptop GPU. Pick the model, do the arithmetic, and defend the trade-offs out loud.
Lesson overview
A turbine technician needs exact torque values from a 32,000-token manual, offline, on a 16 GB laptop GPU. Pick the model, do the arithmetic, and defend the trade-offs out loud.
What you’ll explore
- Choose an architecture for a stated product constraint, back the choice with memory, latency, and training-cost arithmetic, and write an honest trade-off defense with tests that could prove it wrong.
Original explanations, connected to the research.
Artificial Intelligence: A Modern Approach — authors’ materialsModel Cards for Model Reporting (Mitchell et al., 2019)ZeRO: Memory Optimizations Toward Training Trillion Parameter Models (Rajbhandari et al., 2019)Prepare a project review
Give someone the context to challenge your thinking.
Download the authored brief, deliverables, and review criteria with your notes. Use the worksheet for self or peer review. Project artifacts are ungraded here, and this review does not award mastery credit.
Suggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.