Machine-Learning-Course-Resources

This repository contains Jupyter notebooks and labs for a course on the Mathematical Foundation of Machine Learning (MFML). The MFML course explores the application of linear algebra in machine learning and covers topics in multivariable calculus, optimization, and probability. The course incorporates mini-projects as homework assignments that collectively serve as a step-by-step guide for students to complete their final projects independently. MFML is an ongoing course, with more materials to be added.

Topics include:

Linear Algebra:

• LU factorization

• Diagonalization

• The Gram–Schmidt and QR-Factorization

• Least Square problem

• Singular Value Decomposition

• The best rank-k approximation

• Linear Regression

• Forecasting Baseball Team Wins Based on Run Differential

Multivariable Calculus:

• Tensor Calculus
• Backpropagation and Automatic Differentiation

Foundational Models in ML:

• PCA
• Regression
• Neural Network
• SVD

Refrences:

1. Python for linear Algebra, 2023, S. Anbouhi
2. Linear Algebra and Learning from Data, 2019, G. Strang, .
3. MATHEMATICS FOR MACHINE LEARNING, 2020, Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong.
4. Linear Algebra and Optimization for Machine Learning, 2021 by Charu C. Aggarwal.
5. Linear Algebra and its Applications. 5th ed., Pearson., 2016, Lay, David, et al.
6. NEURAL NETWORKS AND DEEP LEARNING: A TEXTBOOK (Second Edition), 2017 Charu C. Aggarwal.