Foundational Mathematics¶

Core mathematical building blocks for machine learning. Start here if you’re new to the math side.

Notebooks¶

#	Notebook	Topics
00	Python ML Libraries	NumPy, Matplotlib, SciPy essentials for ML math
01	Linear Algebra Fundamentals	Vectors, matrices, operations, systems of equations
02	Calculus & Derivatives	Derivatives, chain rule, partial derivatives, gradients
03	Probability & Statistics	Distributions, Bayes’ theorem, expectation, variance
04	Gradient Descent	Optimization basics, learning rate, convergence
05	Information Theory	Entropy, cross-entropy, KL divergence
06	Statistical Inference	Hypothesis testing, confidence intervals, MLE
07	Neural Network Math	Forward pass, backpropagation, loss functions
08	Advanced Linear Algebra	Eigendecomposition, SVD, PCA foundations
09	Analytical vs Numerical	Closed-form vs iterative solutions, numerical stability
10	Control Theory for AI	Control theory connections to RL and optimization
11	Markov Models & HMMs	Markov chains, hidden Markov models, Viterbi
12	Optimization from Scratch	SGD, momentum, Adam optimizer implementation

Prerequisites¶

Python 3.8+
NumPy, Matplotlib

Suggested Order¶

Essential first pass (covers what you need for 90% of ML):

01 Linear Algebra → 02 Calculus → 03 Probability → 04 Gradient Descent

Then pick based on need:

Going into NLP? → 05 Information Theory
Going into neural nets? → 07 Neural Network Math → 12 Optimization
Going into Bayesian ML? → 06 Statistical Inference
Going into sequence models? → 11 Markov Models

Next Steps¶

After completing the essential pass, continue to:

mml-book/ for rigorous math depth
cs229-course/ for ML algorithms
mml-book/practice-labs/ for hands-on implementation