Name: 深度學習解決挑戰性問題（Google I/O'19）。 (Deep Learning to Solve Challenging Problems (Google I/O'19))
Uploaded: 2021-01-14T10:02:02.000Z
Duration: 40 min 59 s
Description: 【看影片學英語】數萬部 YouTube 影片，搭配英漢字典即點即查，輕鬆掌握單字發音與用法，長久累積看電影不必再看字幕。

JEFF DEAN: I'm excited to be here today to tell you

it can be used to solve some of the really challenging problems

And I should point out that I'm presenting

the work of many, many different people at Google.

So this is a broad perspective of a lot of the research

So first, I'm sure you may have all noticed,

but machine learning is growing in importance.

There's a lot more emphasis on machine learning research.

There's a lot more uses of machine learning.

This is a graph showing how many Arxiv papers--

And what you see is that, since 2009, we've actually

been growing the number of papers posted at a really

fast exponential rate, actually faster than the Moore's Law

growth rate of computational power that we got so nice

and used to for 40 years but it's now slowed down.

So we've replaced the nice growth in computing performance

with growth in people generating ideas, which is nice.

And deep learning is this particular form

of a very old set of ideas around creating

These are these collections of simple trainable mathematical

units organized in layers where the higher layers typically

based on things that the lower layers are learning.

And you can train these things end to end.

And the algorithms that underlie a lot of the work

just won the Turing Award this year along with Yann LeCun

that they did over the past 30 or 40 years.

But what's changed is we got amazing results 30 or 40 years

have the computational resources to make these approaches work

But starting about eight or nine years ago,

we started to have enough computation to really make

And so what are things-- think of a neural net as something

that can learn really complicated functions that

You think of functions as like y equals x squared or something.

But really these functions can be very complicated

and can learn from very raw forms of data.

what is in the image as a categorical label like that's

to predict a transcript of what is being said.

You can learn to take input in one language-- hello,

and predict the output being that sentence translated

like take the pixels of an image and create a caption that

A cheetah lying on top of a car, which is kind of unusual

Your priority for that should be pretty low.

we've made great strides thanks to neural nets.

the winning entry did not use neural nets.

The winning entry did not use neural nets.

among 1,000 different categories of things

including like a picture of a dog, you have to say which

And in 2016, for example, the winning entry got 3% error.

You know, computers went from basically not

字幕列表影片播放

深度學習解決挑戰性問題（Google I/O'19）。 (Deep Learning to Solve Challenging Problems (Google I/O'19))

essentially

significant

bunch

slightly