M1 Artificial Intelligence · semester 7 · ML, Symbolic AI
Introduction to AI
Two halves and nine labs. Machine learning runs from a first evaluation metric to recurrent networks; symbolic AI runs from Datalog rules to constraint models.
Two halves, one course
Machine learning
Seven labs, one pipeline at a time
Evaluation metrics, SVMs, clustering, regularisation, deep learning, transfer learning, and recurrent networks.
Symbolic AI
Logic and constraints
Two labs: a Datalog knowledge base and family tree, then the same kind of question answered as a constraint model.
How the work is recorded
Each lab that gets completed carries a steps page: the steps it asks for, and once the notebook is done, what each step decided, what was rejected, and the reference that settled it. A choice without a reference is a guess, so the trail is written down where the code can be read beside it.
Reading it
Source
The folder on GitHub
The two halves, each with its own lab folders and completed notebooks.
README
The course README
The full table of labs across both halves, what each is solved with, and what is provided going in.
The lab subjects, the official corrections, the helper modules and the datasets are not redistributed here. Each lab keeps them on disk, out of the repository; what is committed is the work written against them.