Thanks for tuning in again and welcome to deep learning. In this small video we will

look into the organizational matters and conclude the introduction. Okay, so let's look at the

organizational matters. Now the module that you can obtain here at FAU consists in total

of five ECTS and this is the lecture plus the exercises. So it's not just sufficient

to watch all of these videos. You have to pass the exercises and the exercises you will

implement everything that we're talking about here also in Python and we'll start from scratch.

So you will implement perceptrons, neural networks up to deep learning and in the very end we

will even move ahead towards GPU implementation and also large deep learning frameworks. So

this is a mandatory part. It's not sufficient only to pass the oral exam. The content of

the exercise is Python. We'll do an introduction to Python if you have never used it because

Python is one of the main languages that deep learning implementations use today and you

will really develop a neural network from scratch. There will be feed-forward neural

networks, there will be convolutional neural networks. You will look into regularization

techniques, how you can actually adjust weights such that they have specific properties. You

can see how you can beat overfitting with certain regularization techniques and we will

of course also implement recurrent networks. Later we will use the PyTorch framework and

use that on large scale classification. For the exercises you should bring a basic knowledge

of Python and NumPy. You should know about linear algebra such as matrix multiplication.

Image processing is a definite plus. You should know how to process images and of course requirements

for this class are actually pattern recognition fundamentals and that you have attended the

other lectures of pattern recognition already. You should bring a passion for coding. You

have to code quite a bit but you can also learn it during the exercises. If you have

not done a lot of programming before this class you will spend a lot of time with the

exercises. But if you complete those exercises you will be able to implement things in deep

learning frameworks and this is a very very good training such that you cannot just download

code from GitHub and run it on your own data but you also understand the inner workings

of the networks, how to write your own layers and how to extend deep learning algorithms

also on a very low level. So pay attention pay attention to detail and if you are not

very well used to programming it will cost a bit of time. There will be five exercises

throughout the semester and there's unit tests for all but the last exercise so these unit

tests should help you with the implementations and in the last exercise there will be a PyTorch

implementation and you will be facing a challenge and you have to solve this image recognition

task in order to pass the exercise. Exercise deadlines are announced in the respective

exercise sessions so you have to register to them in StutOn and yeah what we've seen

in the lecture so far is that deep learning is more and more present in the daily life

so it's not just a technique that's done in research we've seen this emerging really into

many many different applications from speech recognition, image processing and so on, autonomous

driving is something that is going to happen probably very soon. Very very quickly maybe

in towards the end of this year but I'd say I'd be shocked if it's not next year at the

latest that having the person having a human intervene will decrease safety. And it's a

very active area of research if you're doing this lecture you have a very good preparation

for a research project with our lab or industry or other partners and yeah we looked into

the perceptron as Bernoulli classifier and their relation to biological neurons. But

it's all going to happen I mean we are going to get to human level intelligence or whatever

you want what you will artificial general intelligence at some point and that's certainly

going to change our place in the food chain because a lot of the tedious things that we

do now we're going to have machines do. So next time on deep learning we will actually

start with the next lecture blog which means we will extend the perceptron to a universal

function approximator. We will look into gradient based training algorithms for these models

and then we also look into the efficient computation of gradients. Now if you want to prepare for