Machine learning lecture 1  (Page 2/17)

Student : iCME.

Instructor (Andrew Ng) : Say again?

Student : iCME.

Instructor (Andrew Ng) : iCME. Cool.

Student : [Inaudible].

Instructor (Andrew Ng) : Civi and what else?

Student : [Inaudible]

Instructor (Andrew Ng) : Synthesis, [inaudible] systems. Yeah, cool.

Student : Chemi.

Instructor (Andrew Ng) : Chemi. Cool.

Student : [Inaudible].

Instructor (Andrew Ng) : Aero/astro. Yes, right. Yeah, okay, cool. Anyone else?

Student : [Inaudible].

Instructor (Andrew Ng) : Pardon? MSNE. All right. Cool. Yeah.

Student : [Inaudible].

Instructor (Andrew Ng) : Pardon?

Student : [Inaudible].

Instructor (Andrew Ng) : Endo —

Student : [Inaudible].

Instructor (Andrew Ng) : Oh, I see, industry. Okay. Cool. Great, great. So as you can tell from a cross-section of this class, I think we're a very diverse audience in this room, and that's one of the things that makes this class fun to teach and fun to be in, I think.

So in this class, we've tried to convey to you a broad set of principles and tools that will be useful for doing many, many things. And every time I teach this class, I can actually very confidently say that after December, no matter what you're going to do after this December when you've sort of completed this class, you'll find the things you learn in this class very useful, and these things will be useful pretty much no matter what you end up doing later in your life.

So I have more logistics to go over later, but let's say a few more words about machine learning. I feel that machine learning grew out of early work in AI, early work in artificial intelligence. And over the last — I wanna say last 15 or last 20 years or so, it's been viewed as a sort of growing new capability for computers. And in particular, it turns out that there are many programs or there are many applications that you can't program by hand.

For example, if you want to get a computer to read handwritten characters, to read sort of handwritten digits, that actually turns out to be amazingly difficult to write a piece of software to take this input, an image of something that I wrote and to figure out just what it is, to translate my cursive handwriting into — to extract the characters I wrote out in longhand. And other things: One thing that my students and I do is autonomous flight. It turns out to be extremely difficult to sit down and write a program to fly a helicopter.

But in contrast, if you want to do things like to get software to fly a helicopter or have software recognize handwritten digits, one very successful approach is to use a learning algorithm and have a computer learn by itself how to, say, recognize your handwriting. And in fact, handwritten digit recognition, this is pretty much the only approach that works well. It uses applications that are hard to program by hand.

Learning algorithms has also made I guess significant inroads in what's sometimes called database mining. So, for example, with the growth of IT and computers, increasingly many hospitals are keeping around medical records of what sort of patients, what problems they had, what their prognoses was, what the outcome was. And taking all of these medical records, which started to be digitized only about maybe 15 years, applying learning algorithms to them can turn raw medical records into what I might loosely call medical knowledge in which we start to detect trends in medical practice and even start to alter medical practice as a result of medical knowledge that's derived by applying learning algorithms to the sorts of medical records that hospitals have just been building over the last 15, 20 years in an electronic format.