> ./paths _ > ./modules > ./articles > ./papers

# ML Fundamentals

Build a rock-solid foundation in machine learning, from linear algebra through training your first neural network.

└─ status: in-progress

3 sections · 5 modules

│ The math you actually need for ML

├─ 1.1 Linear Algebra for ML

Vectors, matrices, and transformations — the language of machine learning computation.

└─ 1.2 Probability and Statistics

Distributions, Bayes' theorem, and the statistical thinking behind every ML algorithm.

│ Gradient descent, loss functions, and optimization

├─ 2.1 Gradient Descent from Scratch

Implement gradient descent in pure Python and visualize how it finds minima in loss landscapes.

python · hands-on · optimization

└─ 2.2 Loss Functions Explained

MSE, cross-entropy, and beyond — understand when and why to use each loss function.

theory · optimization · training

│ Putting it all together with a real neural network

└─ 3.1 Your First Neural Network

Build, train, and evaluate a simple neural network on real data using PyTorch.

pytorch · hands-on · training