Welcome everybody to this semester's deep learning lecture. My name is Andreas

Meyer and I will walk you through this lecture series. So you can see again

that we are still not in the lecture hall but you can see me here in my home

office. We decided to make those videos again available for online learning. You

know the pandemic is still going on. Many of you can't find the way to our

lecture halls. Some of you are still stuck in visa trouble so you can't even

enter the country. Some of you are already here but we try to avoid to fill

our lecture halls with so many students. So we decided to keep up this format

with online video lectures. Again we chose the format of 15 minute video

lectures because they are much easier to consume and we will release those videos

again almost every day such that you can also easily follow the lecture. In total

we will have 65 videos and you can see that when the semester runs from the

start of November until approximately mid of February then you can already

guess how many videos you should have been watching during this entire period.

So I hope you will find these videos here interesting and joyful. Again we

will have two versions of the video series. We have one version that has

quite a few memes that should be a little bit of refreshments during the

scope of the video and we will provide a second version that is not

contaminated by any memes in case you find them distracting. We will just cut

them out and you have this second version that doesn't have any of those

distractions. Okay so thank you very much for tuning in and this means we are

ready to go with our lecture. This first lecture will be about the introduction

into deep learning. We will deal with a broad variety of topics in this lecture

first and foremost of course deep learning. We summarize some of the

buzzwords here that you may have already heard. We cover topics from supervised to

unsupervised learning. Of course we will talk about neural networks, feature

representation, feature learning, big data, artificial intelligence, machine and

representation learning but also tasks such as classification, segmentation,

regression and generation. Let's have a short look at the outline. So first we

will start with our motivation and why we are interested in deep learning. We see

that we have seen tremendous progress over the last couple of years so it

will be very interesting to look into some applications and some breakthroughs

that have been done. In the next videos we want to talk about machine learning

and pattern recognition and how they are related to deep learning and of course

the first set of lectures we want to start from the very beginning. So we will

talk about the perceptron and we will also have to talk about a couple of

organizational matters that you will see in video number five. So let's have a

look into the motivation and what are the interesting things that are

happening right now. First and foremost I want to show you this little graph

about the stock market value of Nvidia shares. You can see here that over the

last couple of years in particular since 2016 the market value has been growing.

One reason why this has been tremendously increasing is that in 2012

the deep learning revolution started and this really took off approximately in

2016. So you can see that many people needed additional compute hardware.

Nvidia is manufacturing general-purpose graphics processing units that allow

arbitrary computation on their boards. In contrast to traditional hardware that

doubles the computing capabilities within every two years graphics boards

double their compute power within approximately 14 to 16 months which

means that they have quite an extraordinary amount of computing power.

This enables us to train really deep networks and state-of-the-art machine