Week 1 - Video 2 - Machine Learning

the rise of AI has been largely driven

by one too in AI called machine learning

in this video you learn what is machine

learning sorted by the end you hope

you'll be able to start thinking how

machine learning might be applied to

your company or to your industry the

most commonly used type of machine

learning as a type of AI that learns A

to B or input to output mappings and

this is called supervised learning let's

see some examples if the input a is an

email and the output B you want is this

email spam one out 0 1 then this is the

core piece of AI used to build a spam

filter or if the input is an audio clip

and the a eyes job is output the text

transfer dentists is speech recognition

more examples if you want to input

English and have it outputs a different

language Chinese Spanish something else

then this is machine translation or the

most lucrative form of supervised

learning of this type of machine

learning may be online advertising where

all the large online ad platforms have a

piece of AI that inputs some information

about an ad and some information about

you and tries to figure out will you

click on this ad or not and by showing

you the answer you most likely click on

this turns out to be very lucrative

maybe not the most inspiring application

but certainly having a huge economic

impact today or if you want to build a

self-driving car one of the key pieces

of AI is in the eye that takes us input

an image and some information from the

radar or from other sensors and outputs

the position of other costs so your

self-driving car can avoid the other

cause or in manufacturing I've actually

done a lot of work in manufacturing

where you take as input a picture of

something you've just made that you such

as a picture of a cell phone coming off

an assembly line this is a picture of a

phone another picture taken by a phone

and you want to output is there a

scratch or zero dancer as some other

defects on this thing you've just

manufactured and this is visual

inspection which is helping

manufacturers

reduce or prevent defects in the things

that they're making this type of AI

called supervised learning just learns

input to output or a to be mappings and

on one hand input output ABB seems quite

limiting but when you find a right

application scenario this can be

incredibly valuable now the idea of

supervised learning has been around for

many decades but it's really taken off

in the last few years why is this when

my friends ask me hey Andrew why is

supervised learning is taking off now

there's a picture I draw for them and I

want to show you this picture now and

you may be able to draw this picture for

others that ask you the same question as

well let's say on the horizontal axis

you plot the amount of data you have

veritas so for speech recognition this

might be the amount of audio data and

transcripts you have in a lot of

industries the amount of data you have

access to has really grown over the last

couple decades thanks to the rise in the

Internet the rise of computers a lot of

what used to be say pieces of paper are

now instead recorded on a digital

computer so we've just been getting more

and more and more data now let's say on

the vertical axis you plot the

performance of an AI system it turns out

that if you used a traditional AI system

then the performance would grow like

this that you feel it more data as the

homes gets a bit better but beyond a

certain point it did not get that much

better so it's as if your speech

recognition system did not get that much

more accurate or your online advertising

system didn't get that much more

accurate at showing the most relevant

ads even as you showed it more data AI

has really taken off recently due to the

rise of neuro networks and deep learning

how to find these terms more precisely

in later videos so don't worry too much

about what it means for now but with

modern a I would neural networks and

deep learning what we saw was that if

you train a small neural network then

the performance kind of looks like this

where as you feed it more data

performance keeps getting better for

much longer and if you train a even

slightly larger neural network say a

medium-sized neural net

then the performance may look like that

and if you train a very large neural

network then the performance just you

know kind of keeps on getting better and

better and for applications like speech

recognition online advertising building

subtitle car we're having a high

performance highly accurate safe speech

recognition system is important this has

enabled these AI systems get much better

and make say sneak recognition products

much more acceptable to users much more

valuable to companies and to users now

here a couple of implications of this

figure if you want the best possible

levels of performance you perform this

to be up here to hit this level of

performance then you kind of meet two

things one is it really helps to have a

lot of data so that's why sometimes you

hear about big data having more data

almost always helps and the second thing

is you want to be able to train a very

large neural network and so the rise of

fast computers including Moore's law but

also the rise of specialized processes

such as graphics processors units or

GPUs which you hear more about in the

later video has enabled many companies

not just a giant tech companies but many

many other companies to be able to train

large neural nets on a large enough

amount of data in order to get very good

performance and drive business value the

most important idea in AI has been

machine learning and specifically

supervised learning which means a 2b or

input/output mappings what enables that

the work really well is data in the next

video let's take a look at what is data

and what data you might already have and

how to think about feeding this into AI

systems let's go on to the next video