Linear Algebra for Machine Learning book
Open the black box of machine learning
Jumping into machine learning has never been easier. But libraries like TensorFlow and PyTorch hide the complexities from you. Looking under the hood is a superpower, and machine learning is written in the language of linear algebra.
This book is the best way to learn it.
Make matrices your most powerful tool
Master linear algebra through intuitive and clear explanations with a focus on machine learning.
Intuitive and clear explanations
Every concept is explained from the ground up, leading with intuition and examples. Mathematics does not have to be complicated.
Math, with machine learning in mind
Focusing on math that is core to machine learning. No distractions, no detours.
Who is this book for?
Machine learning-first approach to linear algebra. Master the art of storing, manipulating, and analyzing data.
Engineers and developers.
All the practical knowledge you need to know about vectors and matrices, with easy explanations you wish you had in school.
Whether it is your first course in linear algebra, or refreshing the topic after years: this book is for you.
What you'll get
What you'll learn
- How data is represented by vectors and matrices,
- What is the optimal way to represent vectors and matrices inside a computer,
- Why is matrix multiplication defined the way it is,
- How to work with vectors and matrices in practice,
- What is the geometric structure of vector spaces,
- Why are vectors and matrices the fundamental building block of machine learning,
- Why are linear transformations essential in machine learning and what do matrices have to do with them,
- What eigenvalues and eigenvectors are and why are they extremely useful in practice,
- Why the Singular Vector Decomposition is the pinnacle result of linear algebra,
Table of contents
- Vectors in theory
- Vectors in practice
- The geometric structure of vector spaces: measuring distances
- Inner products, angles, and lots of reasons to care about them
- The first steps in computational linear algebra
- Matrices, the workourses of machine learning
- Linear transformations
- Determinants, or how linear transformations affect volume
- Linear equations
- The LU decomposition
- Determinants in practice
- Eigenvalues and eigenvectors
- Special transformations and matrix decompositions
- Computing eigenvalues
About the author
Hi there! My name is Tivadar.
I obtained my PhD in 2016 in the field of pure mathematics. As a postdoctoral researcher, I joined a computational biology group, where I fell in love with machine learning.
Understanding mathematics was a cheat code to supercharge my progress.
As I frequently helped my friends and colleagues to master the fundamental concepts of math and machine learning, I found my new passion in teaching.
Since then, education have become my single focus, and my mission is to make quality math education available for developers, engineers, and scientists.
Mathematics of Machine Learning early access
- 400+ pages of mathematics, new chapters delivered continuously
- PDF + jupyter-book format
- Python code examples for all concepts
- Lifetime updates
- Single-variable calculus
- Multivariable calculus
- Probability theory and statistics
- Foundations of machine learning
- Internals of neural networks
Safe and secure payment.
Payments are 100% safe and secure, thanks to Gumroad! No credit card information is received and stored at our end. All data is transmitted via encryption.
100% risk-free money back guarantee.
If you don’t like the book, contact me within 60 days, and I’ll give you a full refund. No questions asked.
Any questions? I am here to help!
If you have any questions, shoot me a message on Twitter @TivadarDanka! I am happy to help!