Explore
For Enterprise
Join for Free
Log In

Artes e Humanas
Negócios
Ciência da Computação
Ciência de Dados
Tecnologia da informação
da saúdesaúde
Matemática e Lógica
Desenvolvimento Pessoal
Ciência e Engenharia Física
Ciências Sociais
Línguas
Diplomas e certificados

Explore todo o Coursera

Navegar
Pesquisar
For Enterprise
Entrar
Inscreva-se gratuitamente

Getting Lots of Data and Artificial Data

Loading...

Aprendizagem Automática

Universidade de Stanford

4.9 (104,970 classificações) | 2.3M alunos inscritos

Visualizar o programa do curso

A Aprendizagem Automática é a ciência que faz com que os computadores exerçam seu papel de forma natural sem que pareçam explicitamente programados para tal. Na última década, a aprendizagem automática foi responsável pelo surgimento dos carros automáticos, por recursos de reconhecimento de fala, otimizou as buscas na web e possibilitou um avanço enorme na compreensão do genoma humano. Atualmente a aprendizagem automática está tão difundida, que você provavelmente a utiliza várias vezes ao dia sem que perceba. Muitos pesquisadores também acreditam que esse é o caminho para levar a inteligência artificial a níveis equivalentes aos humanos. Neste curso, você vai conhecer as técnicas mais eficazes de aprendizagem automática, colocá-las em prática e ver como adequar essas técnicas para suas necessidades. O mais importante é que você não aprenderá apenas na teoria e sim terá o conhecimento prático necessário para aplicar as técnicas de forma rápida e exitosa e solucionar os problemas em seus projetos. Além disso, o aluno conhecerá alguns dos melhores e mais inovadores métodos utilizados no Vale do Silício no que se refere à aprendizagem automática e IA. Este curso traz uma introdução abrangente sobre aprendizagem automática, mineração de dados, e reconhecimento de padrões. Os tópicos estudados incluem: (i) Aprendizagem supervisionada (algoritmos paramétricos e não paramétricos, máquinas vetoriais de suporte, núcleos e redes neurais). (ii) Aprendizagem não supervisionada (Algoritmos de agrupamento - clustering, redução dimensional, sistemas de recomendação, a algoritmos hierárquicos). (iii) A melhores técnicas de aprendizagem automática (viés indutivo / variância; processo de inovação em aprendizagem automática e inteligência artificial). O curso abordará também inúmeros estudos de caso e aplicações para que o aluno possa aprender como aplicar os algoritmos na construção de robôs inteligentes (percepção, controle), reconhecimento de texto (para pesquisa na web, anti-spam), visão computacional, informática médica, áudio, mineração de dados, entre muitas outras áreas de aplicação.</p>

Habilidades que você aprenderá

Logistic Regression, Artificial Neural Network, Machine Learning (ML) Algorithms, Machine Learning

Avaliações

4.9 (104,970 classificações)

5 stars
97,303 ratings
4 stars
7,068 ratings
3 stars
443 ratings
2 stars
74 ratings
1 star
82 ratings

MN

Jun 15, 2016

Excellent starting course on machine learning. Beats any of the so called programming books on ML. Highly recommend this as a starting point for anyone wishing to be a ML programmer or data scientist.

PT

Sep 01, 2018

Sub title should be corrected. Since I'm not that good in English but I know when there're mis-traslated or wrong sub title. If you fix this problems , I thin it helps many students a lot. Thanks!!!!!

Na lição

Application Example: Photo OCR

Identifying and recognizing objects, words, and digits in an image is a challenging task. We discuss how a pipeline can be built to tackle this problem and how to analyze and improve the performance of such a system.

Problem Description and Pipeline7:02

Sliding Windows14:40

Getting Lots of Data and Artificial Data16:20

Ceiling Analysis: What Part of the Pipeline to Work on Next13:50

Ministrado por

Andrew Ng
CEO/Founder Landing AI; Co-founder, Coursera; Adjunct Professor, Stanford University; formerly Chief Scientist,Baidu and founding lead of Google Brain

I've seen over and over that

one of the most reliable ways to

get a high performance machine learning

system is to take

a low bias learning algorithm

and to train it on a massive training set.

But where did you get so much training data from?

Turns out that the machine earnings

there's a fascinating idea called artificial

data synthesis, this doesn't

apply to every single problem, and

to apply to a specific

problem, often takes some thought and innovation and insight.

But if this idea applies

to your machine, only problem, it

can sometimes be a an

easy way to get a

huge training set to give to your learning algorithm.

The idea of artificial

data synthesis comprises of two

variations, main the first

is if we are essentially creating

data from [xx], creating new data from scratch.

And the second is if

we already have it's small

label training set and we

somehow have amplify that training

set or use a small training

set to turn that into

a larger training set and in

this video we'll go over both those ideas.

To talk about the artificial data

synthesis idea, let's use

the character portion of

the photo OCR pipeline, we

want to take it's input image

and recognize what character it is.

If we go out and collect

a large label data set,

here's what it is and what it look like.

For this particular example, I've chosen a square aspect ratio.

So we're taking square image patches.

And the goal is to take

an image patch and recognize the

character in the middle of that image patch.

And for the sake of simplicity,

I'm going to treat these images

as grey scale images, rather than color images.

It turns out that using color

doesn't seem to help that much for this particular problem.

So given this image patch, we'd

like to recognize that that's a

T. Given this image patch,

we'd like to recognize that it's an 'S'.

Given that image patch we

would like to recognize that as an 'I' and so on.

So all of these, our

examples of row images, how

can we come up with a much larger training set?

Modern computers often have a

huge font library and

if you use a word processing

software, depending on what word

processor you use, you might

have all of these fonts and

many, many more Already stored inside.

And, in fact, if you go different websites, there

are, again, huge, free font

libraries on the internet we

can download many, many different

types of fonts, hundreds or perhaps thousands of different fonts.

So if you want more

training examples, one thing you

can do is just take

characters from different fonts

and paste these characters against

different random backgrounds.

So you might take this ---- and paste that c against a random background.

If you do that you now have

a training example of an

image of the character C.

So after some amount of

work, you know this,

and it is a little bit of

work to synthisize realistic looking data.

But after some amount of work,

you can get a synthetic training set like that.

Every image shown on the right was actually a synthesized image.

Where you take a font,

maybe a random font downloaded off

the web and you paste

an image of one character

or a few characters from that font

against this other random background image.

And then apply maybe a little

blurring operators -----of app

finder, distortions that app

finder, meaning just the sharing

and scaling and little rotation

operations and if you

do that you get a synthetic

training set, on what the one shown here.

And this is work,

grade, it is, it takes

thought at work, in order to

make the synthetic data look realistic,

and if you do a sloppy

job in terms of how

you create the synthetic data then it actually won't work well.

But if you look at

the synthetic data looks remarkably similar to the real data.

And so by using synthetic data

you have essentially an unlimited

supply of training examples for

artificial training synthesis And

so, if you use this

source synthetic data, you have

essentially unlimited supply of

label data to create

a improvised learning algorithm

for the character recognition problem.

So this is an example of

artificial data synthesis where youre

basically creating new data from

scratch, you just generating brand new images from scratch.

The other main approach to artificial data

synthesis is where you

take a examples that you

currently have, that we take

a real example, maybe from

real image, and you create

additional data, so as to

amplify your training set.

So here is an image of a compared

to a from a real image,

not a synthesized image, and

I have overlayed this with

the grid lines just for the purpose of illustration.

Actually have these ----.

So what you

can do is then take this

alphabet here, take this image

and introduce artificial warpings[sp?]

or artificial distortions into the

image so they can

take the image a and turn

that into 16 new examples.

So in this way you can

take a small label training set

and amplify your training set

to suddenly get a lot

more examples, all of it.

Again, in order to do

this for application, it does

take thought and it does

take insight to figure out

what our reasonable sets of

distortions, or whether these

are ways that amplify and multiply

your training set, and for

the specific example of

character recognition, introducing these

warping seems like a natural

choice, but for a

different learning machine application, there may

be different the distortions that might make more sense.

Let me just show one example

from the totally different domain of speech recognition.

So the speech recognition, let's say

you have audio clips and you

want to learn from the audio

clip to recognize what were

the words spoken in that clip.

So let's see how one labeled training example.

So let's say you have one

labeled training example, of someone

saying a few specific words.

So let's play that audio clip here.

0 -1-2-3-4-5.

Alright, so someone

counting from 0 to 5,

and so you want to

try to apply a learning algorithm

to try to recognize the words said in that.

So, how can we amplify the data set?

Well, one thing we do is

introduce additional audio distortions into the data set.

So here I'm going to

add background sounds to simulate a bad cell phone connection.

When you hear beeping sounds, that's

actually part of the audio

track, that's nothing wrong with the speakers, I'm going to play this now.

0-1-2-3-4-5.

Right, so you can listen

to that sort of audio clip and

recognize the sounds,

that seems like another useful training

example to have, here's another example, noisy background.

Zero, one, two, three

four five you know

of cars driving past, people walking

in the background, here's another

one, so taking the original

clean audio clip so

taking the clean audio of

someone saying 0 1 2 3

4 5 we can then automatically

synthesize these additional training

examples and thus amplify

one training example into maybe four different training examples.

So let me play this final

example, as well.

0-1 3-4-5 So by

taking just one labelled example,

we have to go through the effort

to collect just one labelled example

fall of the 01205, and by

synthesizing additional distortions,

by introducing different background sounds,

we've now multiplied this one

example into many more examples.

Much work by just automatically

adding these different background sounds

to the clean audio Just

one word of warning about synthesizing

data by introducing distortions: if

you try to do this

yourself, the distortions you

introduce should be representative the source

of noises, or distortions, that

you might see in the test set.

So, for the character recognition example,

you know, the working things

begin introduced are actually kind

of reasonable, because an image

A that looks like that, that's,

could be an image that

we could actually see in a test set.Reflect

a fact And, you know, that

image on the upper-right, that

could be an image that we could imagine seeing.

And for audio, well, we do

wanna recognize speech, even against

a bad self internal connection, against

different types of background noise, and

so for the audio, we're again

synthesizing examples are actually

representative of the sorts of

examples that we want to

classify, that we want to recognize correctly.

In contrast, usually it does

not help perhaps you actually

a meaning as noise to your data.

I'm not sure you can see

this, but what we've done

here is taken the image, and

for each pixel, in each

of these 4 images, has just

added some random Gaussian noise to each pixel.

To each pixel, is the

pixel brightness, it would

just add some, you know, maybe Gaussian random noise to each pixel.

So it's just a totally meaningless noise, right?

And so, unless you're expecting

to see these sorts of pixel

wise noise in your test

set, this sort of

purely random meaningless noise is less likely to be useful.

But the process of artificial

data synthesis it is you

know a little bit of

an art as well and sometimes

you just have to try it and see if it works.

But if you're trying to

decide what sorts of distortions

to add, you know, do

think about what other meaningful

distortions you might add that

will cause you to generate additional

training examples that are at

least somewhat representative of the

sorts of images you expect to see in your test sets.

Finally, to wrap up this

video, I just wanna say

a couple of words, more about

this idea of getting loss

of data via artificial data synthesis.

As always, before expending a lot

of effort, you know, figuring out

how to create artificial training

examples, it's often a good

practice is to make sure

that you really have a low biased

crossfire, and having a

lot more training data will be of help.

And standard way to do

this is to plot the learning

curves, and make sure that

you only have a low

as well, high variance falsifier.

Or if you don't have a low

bias falsifier, you know,

one other thing that's worth trying

is to keep increasing the number

of features that your classifier

has, increasing the number of

hidden units in your network,

saying, until you actually have a

low bias falsifier, and only

then, should you put

the effort into creating a

large, artificial training set, so

what you really want to avoid

is to, you know, spend

a whole week or spend a few

months figuring out how

to get a great artificially

synthesized data set.

Only to realize afterward, that,

you know, your learning algorithm, performance

doesn't improve that much, even when you're given a huge training set.

So that's about my usual advice

about of a testing that

you really can make use

of a large training set before

spending a lot of effort going out to get that large training set.

Second is, when i'm working

on machine learning problems, one question

I often ask the team

I'm working with, often ask my

students, which is, how much work

would it be to get 10 times as much date as we currently had.

When I face a new machine

learning application very often I

will sit down with a team

and ask exactly this question,

I've asked this question over and

over and over and I've

been very surprised how often

this answer has been that.

You know, it's really not that hard,

maybe a few days of work

at most, to get ten times

as much data as we currently

have for a machine

running application and very

often if you can get

ten times as much data there

will be a way to make your algorithm do much better.

So, you know, if you

ever join the product team

working on some machine learning

application product this is

a very good questions ask yourself

ask the team don't be

too surprised if after a

few minutes of brainstorming if your

team comes up with a

way to get literally ten

times this much data, in

which case, I think you would

be a hero to that team,

because with 10 times as

much data, I think you'll really

get much better performance, just from learning from so much data.

So there are several waysand

that comprised both the ideas

of generating data from

scratch using random fonts and so on.

As well as the second idea

of taking an existing example and

and introducing distortions that amplify

to enlarge the training set A

couple of other examples of

ways to get a lot more

data are to collect the

data or to label them yourself.

So one useful calculation that

I often do is, you know,

how many minutes, how many

hours does it take to

get a certain number of

examples, so actually sit down and

figure out, you know, suppose it

takes me ten seconds to

label one example then

and, suppose that, for

our application, currently we

have 1000 labeled examples examples

so ten times as

much of that would be

if n were equal to ten thousand.

A second way to

get a lot of data is

to just collect the data and you label it yourself.

So what I mean by this is

I will often set down and

do a calculation to figure

out how much time, you

know just like how many hours

will it take, how many

hours or how many days will

it take for me or

for someone else to just sit

down and collect ten times

as much data, as we have

currently, by collecting the data ourselves and labeling them ourselves.

So, for example, that, for

our machine learning application, currently

we have 1,000 examples, so M 1,000.

That what we do is sit

down and ask, how long does

it take me really to collect and label one example.

And sometimes maybe it will

take you, you know ten

seconds to label

one new example, and so

if I want 10 X as many examples, I'd do a calculation.

If it takes me 10 seconds to get one training example.

If I wanted to get 10

times as much data, then I need 10,000 examples.

So I do the calculation, how long

is it gonna take to label,

to manually label 10,000 examples,

if it takes me 10 seconds to label 1 example.

So when you do this calculation,

often I've seen many you

would be surprised, you know,

how little, or sometimes a

few days at work, sometimes a

small number of days of work,

well I've seen many teams be very

surprised that sometimes how

little work it could be,

to just get a lot more

data, and let that be

a way to give your learning

app to give you a huge boost

in performance, and necessarily, you

know, sometimes when you've just

managed to do this, you

will be a hero and whatever product

development, whatever team you're working

on, because this can

be a great way to get much better performance.

Third and finally, one sometimes

good way to get a

lot of data is to use

what's now called crowd sourcing.

So today, there are a

few websites or a few

services that allow you

to hire people on

the web to, you know, fairly

inexpensively label large training sets for you.

So this idea of crowd

sourcing, or crowd sourced

data labeling, is something

that has, is obviously, like

an entire academic literature,

has some of it's own complications and

so on, pertaining to labeler reliability.

Maybe, you know, hundreds of thousands

of labelers, around the

world, working fairly inexpensively to

help label data for you,

and that I've just had mentioned,

there's this one alternative as well.

And probably Amazon Mechanical Turk

systems is probably the most

popular crowd sourcing option right now.

This is often quite a

bit of work to

get to work, if you want

to get very high quality labels,

but is sometimes an

option worth considering as well.

If you want to try to

hire many people, fairly inexpensively

on the web, our labels launch miles of data for you.

So this video, we

talked about the idea of

artificial data synthesis of

either creating new data

from scratch, looking, using

the ramming funds as an example,

or by amplifying an

existing training set, by taking

existing label examples and

introducing distortions to it,

to sort of create extra label examples.

And finally, one thing that

I hope you remember from this

video this idea of if

you are facing a machine learning

problem, it is often worth doing two things.

One just a sanity check,

with learning curves, that having more data would help.

And second, assuming that that's the case,

I will often seat down and

ask yourself seriously: what would

it take to get ten times as

much creative data as you

currently have, and not always,

but sometimes, you may be

surprised by how easy that

turns out to be, maybe

a few days, a few weeks at

work, and that can be

a great way to give your learning algorithm a huge boost in performance

Explore nosso catálogo

Registre-se gratuitamente e obtenha recomendações, atualizações e ofertas personalizadas.

O Coursera proporciona acesso universal à melhor educação do mundo fazendo parcerias com as melhores universidades e organizações para oferecer cursos on-line.

© 2019 Coursera Inc. Todos os direitos reservados.

Baixar na App Store

Baixar no Google Play

Coursera
Sobre
Liderança
Carreiras
Lista de cursos
Certificados
Certificados MasterTrack™
Notas
For Enterprise
For Government

Comunidade
Learners
Partners
Developers
Beta Testers
Translators

Conectar
Blog
Facebook
LinkedIn
Twitter
Instagram
YouTube
Tech Blog

Mais
Termos
Privacidade
Ajuda
Acessibilidade
Imprensa
Contato
Diretório
Afiliados