Machine Learning
The rise of AI has been largely driven by
one tool in AI called machine learning.
In this video, you'll learn what
is machine learning so that by the end,
you hopefully 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 is 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,
is this email spam or not?
0/1. Then this is the core piece of
AI used to build a spam filter.
Or if the input A is an audio clip and
the AI's job is output the text transcript,
then this is speech recognition.
More examples, if you want to input
English and have it output 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?
By showing you the ads that you're 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 an AI that takes its input an image,
and some information from
the radar or from other senses and outputs
the position of other cars so your self-
driving car
can avoid the other cars 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
manufactured,
such as a picture of
a cell phone coming off an assembly line.
This is a picture of a phone,
not a picture taken by a phone.
You want to output, is there a scratch or is
there a dent
or some other defect on
this thing you've just manufactured?
This is visual inspection which
is helping manufacturers to
reduce or prevent defects
in the things that they're making.
Supervised learning also lies
at the heart of generative AI systems,
like the ChatGPT and chat bots that
generate texts.
These systems work by
learning from huge amounts of texts.
You download them from the Internet so
that
when given a few words as the input,
the model can predict the next word that
comes after.
These models, which are called
large language models or LLMs,
generate new texts by repeatedly
predicting what is the next word they should
output.
Given the widespread attention on LLMs,
let's look briefly on the next slide
in greater detail at how they work.
Large language models are built by using
supervised learning to train
a model to repeatedly predict the next
word.
For example, if an AI system has read on
the Internet
a sentence like my favorite drink is lychee
bubble tea,
then the single sentence would be turned
into a lot of
A to B data points for
the model to learn to predict the next word.
Specifically, given this sentence,
we now have one data point that says,
given the phrase my favorite drink,
what do you predict is the next word?
In this case, the right answer
is given my favorite drink is,
what do you predict is the next word?
The correct answer is lychee,
and so on until you have
used all the words in the sentence.
This one sentence is turned into
multiple inputs A and outputs B for
the model to learn given a few words as
input,
what is the next word?
When you train a very large AI system on a
lot of data,
say hundreds of billions or even over a
trillion words,
then you get a large language model like
ChatGPT that given an initial piece
of text called a prompt,
is very good at generating
some additional words in response to that
prompt.
The description I presented here does
omit some technical details like how
the model learns to follow instructions
rather than just predict
the next word found on the Internet.
Also how developers make the model
less likely to generate inappropriate
outputs,
such as one that exhibit
discrimination or hand out harmful
instructions.
If you're interested, you can learn more
about
these details in the calls generative AI for
everyone.
At the heart of LLMs though,
is this technology that learns from a lot of
data to predict what is
the next word using supervised learning.
In summary, supervised learning just learns
input,
output, or A to B mappings.
On one hand, input,
output A to B seems quite limiting.
But when you find the right application
scenario,
this turns out to 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 asked me, hey, Andrew,
why is supervised learning taking off now?
There's a picture I draw for them
and I want to show you this picture now.
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 for a
task.
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 of
decades.
Thanks to the rise of
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.
We've just been getting more and more and
more data.
Now let's say on the vertical access,
you plot the performance of an AI system.
It turns out that if you use a traditional AI
system,
then the performance would grow like this.
That as you feed it more data,
its performance gets a bit better.
But beyond a certain point,
it did not get that much better.
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 more data.
AI has really taken off recently due to
the rise of neural networks and deep
learning.
I'll define these terms more precisely in later
videos,
so don't worry too much about what it
means for now.
But with modern AI,
with neural networks, and deep learning,
what we saw was that if you train a small
neural network,
then the performance looks like this.
Where as you feed in more data,
performance keeps getting better for much
longer.
If you train even slightly larger neural
network,
say a medium sized neural net,
then the performance may look like that.
If you train a very large neural network,
then the performance just
keeps on getting better and better.
For applications like
speech recognition, online advertising,
building self-driving car, where
having a high performance,
highly accurate say speech
recognition system is important,
this has enable these AI systems
get much better and make, say,
speech recognition products much
more acceptable to users,
much more valuable to companies and to
users.
Now here are a couple of implications of
this figure.
If you want the best possible levels of
performance,
your performance to be up here,
to hit this level of performance,
then you need two things.
One is it really helps to have a lot of data.
That's why sometimes you hear about big
data.
Having more data almost always helps.
The second thing is you want to
be able to train a very large neural
network.
The rise of fast computers, including
Moore's law,
but also the rise of specialized processors,
such as graphics processor units or GPU's,
which you hear more about in the later
video,
has enabled many companies,
not just the giant tech companies,
but 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.
In fact, it was also this type of
scaling increasing the amount of data and
the size
of the models that was instrumental to
the recent breakthroughs in
training generative AI systems,
including the large language models
that we discussed just now.
The most important idea in AI
has been machine learning and
specifically,
supervised learning, which means A
to B or input output mappings.
What enables it to 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.