Mathematics for Machine Learning and Data Science

This repository contains learning resources, slides, and materials from the course "Mathematics for Machine Learning and Data Science", taught by Luis Serrano and complemented by content from Ian Goodfellow's "Deep Learning" book. This repository is actively under development.

---

📂 Repository Structure

The repository is organized into the following key courses:

Course Title	Weeks	Description
Linear Algebra for Machine Learning and Data Science	Week 1 - 4	Covers foundational concepts in linear algebra applied to ML.
Calculus for Machine Learning and Data Science	Week 1 - 3	Focuses on derivatives, gradients, and optimization techniques.
Probability & Statistics for Machine Learning & Data Science	Week 1 - 4	Explores probability, distributions, and statistical methods.
Numerical Computations	Coming Soon	Advanced numerical techniques for efficient computations.

---

📘 Linear Algebra for Machine Learning and Data Science

Week	Topics Covered
1	Systems of Linear Equations
	- Systems of linear equations (2 & 3 variables)
	- Geometric interpretation
	- Singular vs. nonsingular matrices
	- Linear dependence and independence
	- Determinants
2	Solving Systems of Linear Equations
	- Matrix elimination methods
	- Row echelon form
	- Matrix rank
	- Gaussian elimination
	- Reduced row echelon form
3	Vectors and Linear Transformations
	- Vector operations and properties
	- Linear transformations
	- Matrix operations
	- Neural network applications
	- Practical labs on vector operations
4	Determinants and Eigenvectors
	- Advanced determinant concepts
	- Eigenvalues and eigenvectors
	- Principal Component Analysis (PCA)
	- Linear bases and span

---

📗 Calculus for Machine Learning and Data Science

Week	Topics Covered
1	Functions of One Variable
	- Derivatives and their applications
	- Optimization fundamentals
	- Cost functions in machine learning
2	Multivariate Calculus
	- Gradients and optimization
	- Gradient descent implementation
	- Linear regression applications
3	Advanced Optimization
	- Neural network optimization
	- Backpropagation mathematics
	- Newton's method and applications

---

📙 Probability & Statistics for Machine Learning & Data Science

Week	Topics Covered
1	Probability Fundamentals
	- Basic probability concepts
	- Random variables
	- Common distributions
2	Distribution Analysis
	- Statistical measures
	- Random vectors
	- Multivariate distributions
3	Statistical Methods
	- Sampling techniques
	- Maximum likelihood estimation
	- Bayesian statistics
4	Statistical Testing
	- Confidence intervals
	- Hypothesis testing
	- ANOVA and practical applications

---

📘 Numerical Computations

Status	Details
Coming Soon	Advanced numerical techniques for efficient machine learning computations.

---

🚀 Contribution

Contributions are welcome! If you'd like to add materials, fix issues, or suggest improvements, please submit a pull request or open an issue.

---

Author

Samarth Sharma