A structured repository covering essential mathematics for machine learning, with clear explanations, intuition, and Python implementations.
-
Updated
Mar 24, 2026 - Jupyter Notebook
A structured repository covering essential mathematics for machine learning, with clear explanations, intuition, and Python implementations.
A beginner-friendly collection of Jupyter notebooks covering the essentials of linear algebra with clear NumPy code and visualizations. Topics include vectors, basis, transformations, dot product, determinants, eigenvalues/eigenvectors, matrix inverse, rank, and cross product—ideal for students and self-learners.
production ready implementation of Linear Regression using only NumPy, demonstrating the mathematical foundations from gradient descent to scalable deployment.
Pure Python & NumPy implementations of core supervised and unsupervised machine learning algorithms built from first principles.
A NumPy-only Multilayer Perceptron (MLP) built from first principles to demystify neural networks, backpropagation, and optimization algorithms.
Implementing Linear and Logistic Regression from Scratch using NumPy
Curated roadmap and free resources to learn mathematics for machine learning: Linear Algebra, Calculus, Probability, Statistics, and Optimization with Python code examples.
A structured collection of notes covering the mathematics, classical algorithms, and neural-network concepts that form the foundations of machine learning.
To associate your repository with the math-for-ml topic, visit your repo's landing page and select "manage topics."