12-Week Math for Machine Learning Study Plan
Week 1-2: Linear Algebra Basics
Topics:
- Vectors, dot product, and matrix multiplication
- Transpose, identity, inverse matrices
- Linear combinations and systems of equations
Resources:
- 3Blue1Brown - Essence of Linear Algebra (Ch. 1-6)
- Khan Academy - Linear Algebra (Vector & matrix operations)
- Exercises: Solve small systems of equations, compute dot/cross products
Mini Project: Vector visualizations in 2D using Python/Matplotlib
Week 3-4: Linear Algebra Deep Dive
Topics:
- Rank, null space, column space
- Eigenvalues & eigenvectors
- Diagonalization and SVD
Resources:
- 3Blue1Brown - Videos on SVD & eigenvectors
- Mathematics for ML book - Ch. 2
- Khan Academy - Eigenvectors & linear transformations
Mini Project: PCA from scratch using NumPy (eigen decomposition of covariance matrix)
Week 5-6: Calculus
Topics:
- Derivatives, gradients, partial derivatives
- Chain rule
- Optimization basics (minima, maxima, convexity)
Resources:
- Khan Academy - Calculus 1 & Multivariable (Derivatives, gradients)
- Mathematics for ML book - Ch. 3
- Paul's Notes - Calculus tutorials
Mini Project: Visualize functions & gradients, implement gradient descent for a quadratic function
Week 7-8: Probability & Statistics
12-Week Math for Machine Learning Study Plan
Topics:
- Random variables, probability distributions
- Conditional probability & Bayes' theorem
- Expectation, variance, and standard deviation
- Normal distribution, CLT
Resources:
- Khan Academy - Statistics & Probability
- Mathematics for ML - Ch. 6
- StatQuest (YouTube)
Mini Project: Simulate random variables, plot distributions in Python
Week 9: Statistical Thinking for ML
Topics:
- Hypothesis testing, p-values, confidence intervals
- Covariance and correlation
- Intro to inference in ML
Resources:
- Khan Academy - Inference & Hypothesis Testing
- Book: Think Stats by Allen B. Downey
- SciPy.stats & pandas
Mini Project: Build a small A/B testing simulator
Week 10: Optimization for ML
Topics:
- Gradient descent, stochastic gradient descent
- Learning rates, convergence
- Cost functions (MSE, cross-entropy)
- Intro to convex functions
Resources:
- DeepLearning.ai Math for ML (Calculus track)
- Stanford CS229 Math Notes
- YouTube: Gemert's ML Optimization
Mini Project: Implement linear regression from scratch using gradient descent
Week 11: Math in ML Algorithms
12-Week Math for Machine Learning Study Plan
Topics:
- Linear regression math
- Logistic regression math
- Understanding loss functions, decision boundaries
Resources:
- StatQuest - Regression and logistic regression
- Pattern Recognition and Machine Learning (Bishop)
Mini Project: Implement logistic regression from scratch
Week 12: Capstone - ML with Math from Scratch
Choose one project:
- Linear regression (multiple features)
- Logistic regression with regularization
- PCA on real dataset
- Naive Bayes with Gaussian assumptions
Deliverable: Jupyter Notebook with math derivation, code, visualizations, and explanation