Catalogue · Faculty of Machine Learning
ML 210
Practical Deep Learning for Coders
fast.ai’s top-down classic: train a state-of-the-art image classifier in the first lesson, then peel back the layers until you have implemented a neural net from scratch. Jeremy Howard’s wager is that practitioners learn best by doing first and formalising second — decades of students say he is right. Pairs beautifully with the bottom-up rigour of ML 301.
Syllabus
- transfer learning
- computer vision
- tabular data
- NLP
- model deployment
Held at fast.ai. The materials remain theirs; the structure is ours. Finished it? Record it in your transcript.