Okay, it's after 12, so I want to get started.

So today, lecture eight, we're going to talk about

deep learning software.

This is a super exciting topic because it changes

a lot every year.

But also means it's a lot of work to give this lecture

'cause it changes a lot every year.

But as usual, a couple administrative notes

before we dive into the material.

So as a reminder the project proposals for your

course projects were due on Tuesday.

So hopefully you all turned that in,

and hopefully you all have a somewhat good idea

of what kind of projects you want to work on

for the class.

So we're in the process of assigning TA's to projects

based on what the project area is

and the expertise of the TA's.

So we'll have some more information about that

in the next couple days I think.

We're also in the process of grading assignment one,

so stay tuned and we'll get those grades back to you

as soon as we can.

Another reminder is that assignment two has been out

for a while.

That's going to be due next week, a week from today, Thursday.

And again, when working on assignment two,

remember to stop your Google Cloud instances

when you're not working to try to preserve your credits.

And another bit of confusion, I just wanted to

re-emphasize is that for assignment two you really

only need to use GPU instances for the last notebook.

For all of the several notebooks it's just in Python

and Numpy so you don't need any GPUs for those questions.

So again, conserve your credits,

only use GPUs when you need them.

And the final reminder is that the midterm is coming up.

It's kind of hard to believe we're there already,

but the midterm will be in class on Tuesday, five nine.

So the midterm will be more theoretical.

It'll be sort of pen and paper working through different

kinds of, slightly more theoretical questions

to check your understanding of the material that we've

covered so far.

And I think we'll probably post at least a short sort of

sample of the types of questions to expect.

Question?

[student's words obscured due to lack of microphone]

Oh yeah, question is whether it's open-book,

so we're going to say closed note, closed book.

So just,

Yeah, yeah, so that's what we've done in the past

is just closed note, closed book, relatively

just like want to check that you understand

the intuition behind most of the stuff we've presented.

So, a quick recap as a reminder of what we were talking

about last time.

Last time we talked about fancier optimization algorithms

for deep learning models including SGD Momentum,

Nesterov, RMSProp and Adam.

And we saw that these relatively small tweaks

on top of vanilla SGD, are relatively easy to implement

but can make your networks converge a bit faster.

We also talked about regularization,

especially dropout.

So remember dropout, you're kind of randomly setting

parts of the network to zero during the forward pass,

and then you kind of marginalize out over that noise

in the back at test time.

And we saw that this was kind of a general pattern

across many different types of regularization

in deep learning, where you might add some kind

of noise during training, but then marginalize out

that noise at test time so it's not stochastic

at test time.

We also talked about transfer learning where you

can maybe download big networks that were pre-trained

on some dataset and then fine tune them for your

own problem.

And this is one way that you can attack a lot of problems

in deep learning, even if you don't have a huge

dataset of your own.

So today we're going to shift gears a little bit

and talk about some of the nuts and bolts

about writing software and how the hardware works.

And a little bit, diving into a lot of details

about what the software looks like that you actually

use to train these things in practice.

So we'll talk a little bit about CPUs and GPUs

and then we'll talk about several of the major

deep learning frameworks that are out there in use

these days.

So first, we've sort of mentioned this off hand

a bunch of different times,

that computers have CPUs, computers have GPUs.

Deep learning uses GPUs, but we weren't really

too explicit up to this point about what exactly

these things are and why one might be better

than another for different tasks.

So, who's built a computer before?

Just kind of show of hands.

So, maybe about a third of you, half of you,

somewhere around that ballpark.

So this is a shot of my computer at home

that I built.

And you can see that there's a lot of stuff going on

inside the computer, maybe, hopefully you know

what most of these parts are.

And the CPU is the Central Processing Unit.

That's this little chip hidden under this cooling fan

right here near the top of the case.

And the CPU is actually relatively small piece.

It's a relatively small thing inside the case.

It's not taking up a lot of space.

And the GPUs are these two big monster things

that are taking up a gigantic amount of space

in the case.

They have their own cooling,

they're taking a lot of power.

They're quite large.

So, just in terms of how much power they're using,

in terms of how big they are, the GPUs are kind of

physically imposing and taking up a lot of space

in the case.

So the question is what are these things

and why are they so important for deep learning?

Well, the GPU is called a graphics card,

or Graphics Processing Unit.

And these were really developed, originally for rendering

computer graphics, and especially around games

and that sort of thing.

So another show of hands, who plays video games at home

sometimes, from time to time on their computer?

Yeah, so again, maybe about half, good fraction.

So for those of you who've played video games before

and who've built your own computers,

you probably have your own opinions on this debate.

[laughs]

So this is one of those big debates in computer science.

You know, there's like Intel versus AMD,

NVIDIA versus AMD for graphics cards.

It's up there with Vim versus Emacs for text editor.

And pretty much any gamer has their own opinions

on which of these two sides they prefer

for their own cards.

And in deep learning we kind of have mostly picked

one side of this fight, and that's NVIDIA.

So if you guys have AMD cards,

you might be in a little bit more trouble if you want

to use those for deep learning.

And really, NVIDIA's been pushing a lot for deep learning

in the last several years.

It's been kind of a large focus of some of their strategy.

And they put in a lot effort into engineering

sort of good solutions to make their hardware

better suited for deep learning.

So most people in deep learning when we talk about GPUs,

we're pretty much exclusively talking about NVIDIA GPUs.

Maybe in the future this'll change a little bit,

and there might be new players coming up,

but at least for now NVIDIA is pretty dominant.

So to give you an idea of like what is the difference

between a CPU and a GPU, I've kind of made a little

spread sheet here.

On the top we have two of the kind of top end Intel

consumer CPUs, and on the bottom we have two of

NVIDIA's sort of current top end consumer GPUs.

And there's a couple general trends to notice here.

Both GPUs and CPUs are kind of a general purpose

computing machine where they can execute programs

and do sort of arbitrary instructions,

but they're qualitatively pretty different.

So CPUs tend to have just a few cores,