Name: Deep Learning of Representations
Uploaded: 2013-03-29T04:52:54.000Z
Duration: 1 h 15 min 44 s
Description: VoiceTubeの動画で発音を聞きながら英語表現を覚えよう！学べる英語：

I'll talk about representations and learning

And the word deep here, I'll explain what it means.

So my goal is to contribute to building intelligent machines,

And how do we get a machine to be smart--

tried to give the knowledge to the machine--

And it didn't work quite as well as was hoped.

One reason is that a lot of our knowledge is not something

So that knowledge has to be taken somewhere else.

And basically what we have found is you can get that

knowledge through observing the world around us.

What it is about is generalizing from the examples

And what I like to tell my students is it's taking

probability mass-- that is, on the training examples and

somehow guessing where it should go-- which new

At first we can measure [INAUDIBLE] we can guess.

And I'll mention something about dimensionality and

geometry that comes up when we think about this [INAUDIBLE].

And one of the messages will be that we can maybe fight

problem by allowing the machine to discover underlying

causes-- the underlying factors that explain the data.

And this is a little bit like [INAUDIBLE] is about.

So let's start from learning, an easy [INAUDIBLE]

Let's say we observe x,y pairs where x is a number--

And the stars here represent the examples we've seen of x,y

So we want to [? generalize ?] for new configurations.

In other words, for example, in this problem, typically we

And there's an underlying relationship between y and x,

meaning the expected value of the y given x, which is given

That's the problem with machine learning.

This is the predicted or learned function.

One of the most basic principles by which machine

learning algorithms are able to do this is assume something

very simple about the world around us-- about the data

we're getting or the function we're trying to discover.

It's just assuming that the function we're trying to

discover is smooth, meaning if I know the value of the

function that's come from the x, and I want to know the

value at some nearby point x prime, then it's reasonable to

assume that the value x prime of the function we want to

I mean, you can formalize that and [INAUDIBLE] in many

different ways and exploit it in many ways.

And what it means here is if I ask you why

what I'm going to do is look up the value of y that I

And if I do that on problems like this, it's actually going

And a large fraction of the applications that we're

But if we only rely on this principle virtualization,

That's one of the messages I want to explain here.

Well, basically we're doing some kind of interpolation.

the green stars here-- to cover the ups and down of the

function I'm trying to learn, then I'm going to be fine.

But what if the function I want to learn has many more

字幕リスト動画再生

Deep Learning of Representations

learn

number

small

kind