Pathway / Computing
Computing from procedure to learning systems
Make procedures explicit, reason about data and cost, then cross the boundary from software systems into evaluated machine learning.
- Route
- 5 connected lessons
- Access
- Open without an account
- Evidence
- Retrieval + transfer, never an opaque percentage
Continuous spine
Start where your evidence starts.
Procedures and state
Read programs as precise transformations of state, beginning with Python.
42 min02Data and invariants
Choose representations by the promises your program must preserve.
47 min03Algorithms and cost
Compare procedures by how their required work grows, not by one stopwatch reading.
55 min04Ownership and systems
Use Rust ownership to make resource lifetime and aliasing part of the program's structure.
61 min05Learning systems and evaluation
Treat a trained model as one component in an evidence-producing system.
64 minA route, not a rank
Evidence changes the next step.
Atlas records learning as unseen, developing, demonstrated, or needs refresh. Demonstrated requires unhinted evidence in two different forms, including delayed retrieval or transfer. A later miss asks for refresh; it does not erase earlier work.
Read the learning evidence policy