Mathematics for Machine Learning and Data Science
Published:
Course 1: Linear Algebra Fundementals
- Topics Covered: Systems of Equations, Vectors, Matrices, Norms, Determinants, Rank of a Matrix, Inverse & Identity Matrices, Matrix Multiplication, Row-Reduction, Linear independence, spans, basis sets, Eigenvalues and Eigenvectors
- Projects & Code: Here
- Course Notes: Here
Course 2: Single and Multi-variable Calculus
- Topics Covered: Derivatives, Gradients and Gradient Descent, Linear Regression, Neural Networks, Optimizing NNs, Newton’s Method, Classification, Backpropogation, Hessian, Convex and Concave functions, Higher Dimensional Calculus
- Projects & Code: Here
- Course Notes: Here
Course 3: Probability & Statistics for Data Science and Machine Learning
- Topics Covered: Probability, Discrete & Continous distributions, Bayesian Statistics, Multivariate Distributions, Sampling & Point Estimation, Confidence Intervals, Hypothesis Testing, A/B Testing
- Projects & Code: Here
- Course Notes: Here
Additional Resources
- Linear Algebra for Deep Learning by Ian Goodfellow and Yoshua Bengio
- Linear Algebra for Machine Learning by Standford University
- Linear Algebra I Course Notes by Tyler Holden
- Calculus Overview for Machine Learning by MIT
- Short Review on Calculus by ML mastery
- Probability Theory Review by Standford University
- Probability Overview Notes by Standford University