Trace transformer attention from its core architecture to a specialized forecasting model.
A technical progression from transformer fundamentals and a transparent spreadsheet-scale implementation to attention variants and the Informer time-series architecture. Learners connect architectural choices to sequence structure, computational costs, and forecasting assumptions, then propose an evaluation that avoids temporal leakage. The selected videos are English-language uploads; original study guidance and assignments emphasize analysis rather than reproducing any video's transcript.
Explain how attention-based transformer components represent relationships across sequence positions. Compare a conventional transformer with an attention variant and a time-series-specific architecture. Design a forecasting evaluation that respects chronology, baselines, and data-leakage risks.
Prior exposure to neural networks, vectors, and basic supervised learning is recommended. Comfort reading simple model diagrams or pseudocode will help; no particular software is required.
Experienced learners who want to deepen and apply advanced AI skills
People who learn best through examples, guided lessons, and hands-on practice
Professionals, creators, and independent builders looking for a repeatable workflow
Lesson 1 is free
4 lessons · Advanced · Full course.
This course uses CC BY licensed material attributed to its content provider or uploader. Lesson playback is available only through authenticated access after publication and licensing checks pass.