Week 1
Functions, graphs and AI intuition
Connect functions, slopes and curves to machine learning models.
FunctionsGraphsML intuition
Detailed learning path
Mathematics for AI
An 8-week foundation track for students who want to understand ML and DL from first principles, including calculus, vectors, matrices and optimization.
Weekly roadmap
What you will learn week by week
Inspired by portfolio-first learning platforms: each module has a clear outcome, practice activity and project artifact.
Week 2
Limits and derivatives
Understand rate of change and why derivatives matter in training models.
LimitsDerivativesPractice
Week 3
Partial derivatives and gradients
Move from single-variable calculus to multi-variable model parameters.
GradientsLoss functions
Week 4
Linear algebra essentials
Vectors, matrices, dot products and transformations for ML.
VectorsMatricesDot product
Week 5
Probability and statistics basics
Probability, distributions, mean, variance and model uncertainty.
ProbabilityStatistics
Week 6
Optimization by hand
Understand minima, maxima, convexity and numerical optimization.
OptimizationConvexity
Week 7
Gradient descent by hand
Calculate gradient descent updates step by step.
Gradient descentLearning rate
Week 8
Mini-project and revision
Build a visual notebook explaining linear regression training mathematically.
NotebookPortfolio
Capstone project
Gradient Descent Visual Notebook
Create a notebook that trains a simple regression model and explains each update by hand.
PythonNumPyMathematics