✨ Math Behind AI: A Linear Algebra Journey
A step-by-step exploration of the essential linear algebra concepts that power modern AI and machine learning. From vectors and matrices to eigenvalues, SVD, and optimization, this series is both my learning path and a shared guide for anyone who wants to understand the math that makes AI work.
Articles in this series
Tech Insights & Engineering Articles
Explore technical articles, software architecture deep dives, clean code tutorials, and computer science explorations from my journey.
Projection onto a Line — The Hidden Geometry Behind Prediction
Imagine trying to predict a value using a model. You have data points scattered in space. But your model can only prod…
Orthogonality — When Information Doesn’t Interfere
Imagine trying to listen to two people talking at the same time.
Angle & Cosine Similarity — How AI Understands Meaning
Sometimes two sentences can look very different but still mean the same thing.
Distance Between Vectors — How AI Understands Closeness
When we say two things are **similar**, what do we really mean?
Vector Length (Norm) — How Strong Is a Signal?
In the previous post, we learned that the dot product measures alignment. Two vectors pointing in the same direction pr…
The Dot Product — The Smallest Idea Behind Modern AI
People often imagine AI as layers, networks, attention mechanisms, and billions of parameters.But deep inside all that c…
Left Null Space — The Error Your Model Cannot Learn
At some point a model stops improving, but not in a dramatic way. The loss doesn’t blow up. It doesn’t fluctuate. It sim…
Null Space: The Directions a Model Quietly Ignores
When we learn linear algebra, we usually focus on what **changes the output**.But in real systems — especially in machin…
Rank: When More Numbers Don’t Mean More Understanding
When I first encountered matrices, I assumed that adding more rows or columns automatically made a system richer. More d…