1.1 Machine learning lecture 2

Instructor (Andrew Ng) :All right, good morning, welcome back. So before we jump into today's material, I just have one administrative announcement, which is graders. So I guess sometime next week, we'll hand out the first homework assignment for this class.

Is this loud enough, by the way? Can people in the back hear me? No. Can you please turn up the mic a bit louder? Is this better? Is this okay? This is okay? Great.

So sometime next week, we'll hand out the first problem sets and it'll be two weeks after that, and the way we grade homework problems in this class is by some combination of TAs and graders, where graders are usually members – students currently in the class.

So in maybe about a week or so, I'll email the class to solicit applications for those of you that might be interested in becoming graders for this class, and there's usually sort of a fun thing to do. So four times this quarter, the TAs, and the graders, and I will spend one evening staying up late and grading all the homework problems.

For those of you who that have never taught a class before, or sort of been a grader, it's an interesting way for you to see, you know, what the other half of the teaching experience is. So the students that grade for the first time sort of get to learn about what it is that really makes a difference between a good solution and amazing solution. And to give everyone to just how we do points assignments, or what is it that causes a solution to get full marks, or just how to write amazing solutions. Becoming a grader is usually a good way to do that.

Graders are paid positions and you also get free food, and it's usually fun for us to sort of hang out for an evening and grade all the assignments. Okay, so I will send email. So don't email me yet if you want to be a grader. I'll send email to the entire class later with the administrative details and to solicit applications. So you can email us back then, to apply, if you'd be interested in being a grader.

Okay, any questions about that? All right, okay, so let's get started with today's material. So welcome back to the second lecture. What I want to do today is talk about linear regression, gradient descent, and the normal equations. And I should also say, lecture notes have been posted online and so if some of the math I go over today, I go over rather quickly, if you want to see every equation written out and work through the details more slowly yourself, go to the course homepage and download detailed lecture notes that pretty much describe all the mathematical, technical contents I'm going to go over today.

Today, I'm also going to delve into a fair amount – some amount of linear algebra, and so if you would like to see a refresher on linear algebra, this week's discussion section will be taught by the TAs and will be a refresher on linear algebra. So if some of the linear algebra I talk about today sort of seems to be going by pretty quickly, or if you just want to see some of the things I'm claiming today with our proof, if you want to just see some of those things written out in detail, you can come to this week's discussion section.