Week 2: Data & Representations

• Lecture 1: The geometry of linear equations
• Condensed version of linear algebra applied to deep learning
• Lecture 2: Elimination with matrices

---

Week 3: Transformations

📄 A 4-page overview of linear algebra

• [ST]: Chapter 8.1, 8.2, 10.6 (more theoretical details)

• [CO]: Chapter 3 (skip section 3.2.8 and 3.3.3) (Ignore at first view his comments on eigenvalues – we will discuss these later in the course.)

• A 4-page overview of linear algebra (PDF)

• Chapter 8.1, 8.2, 10.6 (more theoretical details)

• Chapter 3 (skip sections 3.2.8 and 3.3.3)

• Lecture 30: Linear transformations and their matrices

• Linear Transformation between dimensions

• Matrix Transpose: Visual intuition

---

Week 4: Least Squares

The Stang book contains numerous examples of the topics covered in the lecture notes ([DW]). Refer to these examples if you encounter any concepts that are unclear.

• The Art of Linear Algebra (PDF)
• Lecture 5 – Transposes, Permutations, Spaces Rⁿ
• The Column Space of a Matrix (MIT 2020 Vision)
• Lecture 15 – Projections onto Subspaces

  Essence of Linear Algebra – Projections

---

Week 5: Model Complexity and Generalization

(Coming soon...)

• Kernels

---

Week 6: Understanding Data and Uncertainty

• EliteDataScience Primer
• RANSAC
  

  Ransac

• Covariance Explanation
• Multivariate Normal Distribution (Towards Data Science)
• Regression (curvefitting) with noise
• Tutorials and pdfs

---

Lecture 7: Noise and Filtering

Bias Variance on Kaltura

---

Lecture 8: Classification

• Machine Learning – Week 3 (Coursera)

---

Lecture 9: Advanced Classification and Evaluation

• Chapters 4.3 and 4.4 – Measures of Distance and Measures of Similarity
• Tutorial on evaluation metrics (Part 1)
• Part 2: Evaluation Metrics
• Part 3: Evaluation Metrics
• Matthews Correlation Coefficient – When to Use and When to Avoid
• Precision-Recall Example – scikit-learn

• Precision vs. Recall explained visually

• F1 Score – clearly explained

Supplementary

• Sections 3.2.4, 3.4, 3.5
• Evaluation of models with class-imbalanced data

---

Lecture 10: Variability and PCA

• Machine Learning: SVD & PCA (Jonathan Hui)
• A Brief Introduction to Statistical Shape Analysis
• Eigenvectors and Eigenvalues: A Deeper Understanding (Abdullah Bilal)
• Chapters 7.1, 7.3
• PCA Clearly Explained – When, Why, and How (TDS)

Extra

• Eigenvectors and Eigenvalues (Duplicate – Abdullah Bilal)
• OpenCV Eigenfaces for Face Recognition (PyImageSearch)

Missing PDF: "PCA clearly explained — When, Why, How to use it and feature importance" by Serafeim Loukas (Towards Data Science)

---

Lecture 11: PCA II and Clustering

Lecture 12: Regularization & Non-linear models

Lecture 13: Neural networks

Lecture 14: Neural architectures and Exam