# Python & Mathematics for ML

- **Part of:** [AI & Machine Learning](/en/tracks/ai-machine-learning) — learning path 1 of 3
- **Length:** 4 chapters · 21 lessons · 10 hours a week
- **Level:** Intermediate

::route
1. **Python & Mathematics for ML** — 4 chapters · 10 hours a week · 1 checkpoint
2. [Machine Learning Fundamentals](/en/paths/machine-learning-fundamentals) — 4 chapters · 12 hours a week · 1 checkpoint
3. [ML Engineering & Deployment](/en/paths/ml-engineering-deployment) — 3 chapters · 8 hours a week · 1 checkpoint
::

::cta https://app.artimend.com/tracks/ai-machine-learning Start this track

## Syllabus

### 1. Python Scientific Stack

- 6 lessons
- **Skills:** NumPy · pandas · Jupyter · SciPy

### 2. Linear Algebra for ML

- 5 lessons
- **Skills:** Vectors · Matrices · Eigenvalues · SVD · PCA

### 3. Calculus & Optimization

- 5 lessons
- **Skills:** Derivatives · Gradients · Gradient Descent · Backpropagation

### 4. Probability & Statistics for ML

- 5 lessons
- **Skills:** Probability · Bayesian Reasoning · Probability Distributions · Maximum Likelihood Estimation
- **Checkpoint:** Math Foundations Gate

## Checkpoints

To pass each checkpoint you hand in a piece of real work. What each one asks for:

- **Math Foundations Gate:** Implement linear regression from scratch in NumPy: derive the closed-form solution, fit a model, compute R². Run a Bayes-rule update on a small dataset and explain the prior/likelihood/posterior.