Foundations course
Machine Learning Foundations
A first-principles introduction to modern machine learning.
Linear models through deep networks, with daily problem sets and a capstone project.
Enroll and begin ↗The course
“A first-principles introduction to modern machine learning.”
Students and mid-career professionals making the jump into ML. Every module is organized around applied evidence rather than passive completion.
Curriculum / 04 modules
From first question
to working outcome.
01Weeks 1–3: Foundations+
Probability, useful linear algebra, gradient descent, linear and logistic regression.
- Probability for modeling
- Linear algebra in practice
- Gradient descent and regression
02Weeks 4–6: Classical ML+
Trees, ensembles, regularization, and model selection.
- Trees and ensembles
- Regularization
- Model selection
03Weeks 7–9: Neural networks+
Backpropagation, PyTorch, CNNs, sequence models, and transformers.
- Backpropagation
- Networks in PyTorch
- Modern architectures
04Weeks 10–12: Capstone+
A real dataset, a real question, a written report, and technical defense.
- Question and dataset
- Experimentation
- Report and defense
What changes
You leave able to own the whole engagement.
- 01Implement core ML algorithms from scratch
- 02Train and evaluate neural networks
- 03Debug models that are not learning
- 04Read and reproduce results from papers
- 05Defend a capstone project
Who it is for
Strong builders moving closer to the problem.
Students and mid-career professionals making the jump into ML.
Before you begin
- First-year university linear algebra and calculus
- Programming experience in any language
Enrollment open
Start with the first lesson.
Enroll to save progress, resume across devices, and keep your course work connected to your learner profile.
Enroll and begin ↗