Name: 用TensorFlow構建AI：概述（TensorFlow @ O'Reilly AI大會，舊金山'18）。 (Building AI with TensorFlow: An Overview (TensorFlow @ O’Reilly AI Conference, San Francisco '18))
Uploaded: 2021-01-14T10:03:51.000Z
Duration: 42 min 53 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。

程度副詞

So Laurence gave us a very nice introduction

to what is machine learning and a glimpse

So at Google, we saw the enormous potential

to releasing TensorFlow as an open source platform

that was to give everyone access to this open source library,

the progress and pace of the development of machine

grown to become the number 1 repository on GitHub

proud to have been named as the most loved software library

or framework in the 2018 Stack Overflow Developer Survey.

So all of this success, actually, in large part

is due to the very enormous group of users and developers

that we have out there who are using TensorFlow and building

We are blown away by these download numbers.

and vast majority of them being non-Google contributors.

And you see very active engagement by the TensorFlow

Engineering team with the community in answering issues

If you look at where our users come from,

So these are self-identified locations from our users

and you'll see that they come from every time zone

down in the south, right up to Antarctica,

and right up in the Arctic Circle in Norway.

And I think I see a dot there in Ireland as well, which

So it's used everywhere for a wide variety of things.

So let me switch gears and talk a little bit

about the architecture of TensorFlow-- what

So I'll talk briefly about the APIs that it has,

and then describe the platforms and the languages

that it supports, and then take a quick look

at some of the tooling that really makes it

as a very useful platform for doing machine

learning and letting you do a very versatile set of things.

fundamentally it's a computation execution engine.

And by that, what we mean is that you called your machine

as Laurence was showing in that example--

and then TensorFlow automates all the mechanics

of the training process and of running it

on your device of interest, and lets you build that model

and then use it in practical applications.

So you do this by using these higher-level APIs

as a library for developing machine learning models,

and TensorFlow has full tight integration with Keras,

and in fact, Keras is the preferred high-level way

using these LEGO bricks, which let you piece together models

one layer at a time and build pretty complex architectures.

In addition, we also package some of these very commonly

and these packaged models are battle tested and hardened,

based on architectures that have already proven to be valuable.

in customizing things and changing things

and wiring them anyway you need to for your application.

So these APIs for model building are fed by data,

is very flexible libraries for building these data pipelines--

and then doing some of the feature transformation

that it's ready to be ingested by a machine learning model.

which basically deals with abstracting away your model

and distributing your training job to run

or even on custom architectures such as TPUs,

which we'll talk a little bit more about as we go forward.

用TensorFlow構建AI：概述（TensorFlow @ O'Reilly AI大會，舊金山'18）。 (Building AI with TensorFlow: An Overview (TensorFlow @ O’Reilly AI Conference, San Francisco '18))

字幕列表影片播放

用TensorFlow構建AI：概述（TensorFlow @ O'Reilly AI大會，舊金山'18）。 (Building AI with TensorFlow: An Overview (TensorFlow @ O’Reilly AI Conference, San Francisco '18))

individual

enormous

access

basically