# Summary

# Lectures

Lecture 1: Slides
Lecture 2: Slides

Lecture 1 Part 1 (Admin): Link
Lecture 1 Part 2 (Supervised learning): Link
Lecture 1 Part 3 (Perceptron learning): Link
Lecture 2 Part 1 (Loss functions): Link
Lecture 2 Part 2 (Logistic regression): Link
Lecture 2 Part 3 (Convexity): Link

I recorded a video going through the M1 questions while review some of the math concepts: Link, you do not have to watch this and lecture 2 part 3 if you have taken Calculus 2 and (Linear) Algebra 1.
Last year's perceptron update rule explanation perhaps is clearer: Link
I forgot to mention in the video that we are starting with machine learning (the more difficult half) and we will cover search and games (the easier half) after the midterm. The order of the topics is reversed from the course in fall and winter semesters, but by the end of the summer, we will have covered the same materials.
For Robert Downey Jr. fans, his 2 min intro to AI is great: Link, although it's not what we will do in this course

# Other Materials

Which face is real? Link
Guess two-thirds of the average? Link
Gradient Descent. Link
Eigenvalue in Endgame. Link
Plot 3D functions: Link

Stat

Why does the (batch) perceptron algorithm work? Link
Why cannot use linear regression for binary classification? Link
Why does gradient descent work? Link
How to derive logistic regression gradient descent step formula? Link
Example (Quiz): Perceptron update formula Link
Example (Quiz): Gradient descent for logistic activation with squared error Link
Example (Quiz): Computation of Hessian of quadratic form Link
Example (Quiz): Computation of eigenvalues Link
Example (Homework): Gradient descent for linear regression Link

Checklist: Link, "math crib sheet" under "10/11"
Multivariate Calculus: Textbook, Chapter 16 and/or (Economics) Tutorials, Chapters 2 and 3.
Linear Algebra: Textbook, Chapters on Determinant and Eigenvalue.
Probability and Statistics: Textbook, Chapters 3, 4, 5.