IIIProgram
Applied Machine Learning
Classical ML and the math that underwrites it.
- 301Course
Linear Algebra for ML
The math the field is written in.
6 lessons·PractitionerVectors and matricesDecompositions - 302Course
Probability for ML
Uncertainty, precisely.
7 lessons·PractitionerProbabilityInference - 303Course
Optimization and Gradient Descent
How models actually learn.
6 lessons·PractitionerThe theoryThe modern toolbox - 304Course
Feature Engineering
The 80% of applied ML.
5 lessons·PractitionerThe craftThe discipline - 305Course
Regression
The most-used model.
5 lessons·PractitionerLinear regressionRegularization - 306Course
Classification
The other half of supervised learning.
6 lessons·PractitionerLogistic regressionTrees and ensembles - 307Course
Neural Networks
The building block of modern AI.
6 lessons·PractitionerThe MLPTraining in practice - 308Course
CNNs
Vision's workhorse.
5 lessons·PractitionerThe primitiveModern vision - 309Course
RNNs and Sequence Models
Before transformers, and after.
3 lessons·PractitionerThe RNN family - 310Course
Transformers (Applied)
The architecture, from scratch.
4 lessons·PractitionerFrom scratch - 311Course
Embeddings and Representation Learning
How meaning becomes math.
4 lessons·PractitionerThe techniques - 312Course
Transfer Learning and Foundation Models
Standing on shoulders.
4 lessons·PractitionerThe paradigm