Welcome everyone to today's lecture, where we'll give an introduction to the basic concepts

and the history of machine learning.

This eventually led to the hype in artificial intelligence that we experience today.

And before I start with my presentation, I would give a special thanks to Jonas Adler

and Ozan Öktöm from KTH Stockholm, who allowed me to recycle some of their slides such that

I didn't have to start my presentation from scratch.

Okay, before we start here, some opinions on artificial intelligence in general.

So this quote comes from Jan LeCun, and he's a computer scientist famous among the people

in deep learning.

He was one of the first to use convolutional neural networks for the task of recognition

of handwritten digits.

And his opinion on AI is that our intelligence is what makes us human, and AI is an extension

of that quality.

So he seems to be rather positive about the current trend in artificial intelligence.

Another opinion is by Elon Musk, which you probably know.

He is the CEO of Tesla and SpaceX, two huge companies, and one of the inventors of PayPal

and obviously a visionary in technological insights.

So his opinion on AI is that AI doesn't have to be evil to destroy humanity.

If AI has a goal and humanity just happens to be in the way, it will destroy humanity

as a matter of course, without even thinking about it.

No hard feelings.

So he has kind of a dystopian view on AI.

And there is the late Stephen Hawking, who's more in a mixed feeling about AI, saying that

AI is likely to be either the best or worst thing to happen to humanity.

So he's not very, very decided on that topic.

So everyone has to find out on his own what his feelings are about AI.

And we are trying to give you the basic insights in machine learning and deep learning such

that you can have a profound knowledge to build your opinion upon.

So first of all, where are we in the context of data science?

So in data science, we already talked about data processing, a little bit about data visualizations

and about statistics.

But now we will focus on the right hand side of this structural overview, namely on the

part about machine learning, which is this part here.

And we will talk today about the different paradigms in machine learning that we will

face and especially focus on the one which is called supervised learning, which I will

introduce in a minute.

So this will be the main focus of our lectures in the coming weeks.

So first of all, what is machine learning?

If I may quote Wikipedia, this is what Wikipedia writes about machine learning.

Machine learning is the study of computer algorithms that improve automatically, that's

important, through experience.

It is seen as a subset of artificial intelligence.

Another other word.

Machine learning algorithms build a mathematical model based on sample data known as training

data in order to make predictions or decisions without being explicitly programmed to do

so.

So what's important here is that we have the word automatically and we have this word training

data.

So there must be some input to our algorithms such that they can learn, which is already

in the term machine learning.