Streuspanne-Lexicon

Why do you need the binomial distribution and what is it anyway?

As usual: explained briefly and clearly – in under five minutes.

In statistics, degrees of freedom describe the number of independent pieces of information that are included in an estimate. 

The confidence interval is a range in which an unknown parameter is assumed to lie. The wider this range is, the more likely it is that the unknown value will be covered.

Critical values are used to determine the significance of results in statistical analyses. They therefore help to determine whether an observed effect is based on chance or is actually significant.

What is the mathematical definition of an estimate? And how can I even define something so »imprecise«? In the »Streuspanne-Lexicon«, the team explains briefly and concisely using the example of the coin toss.

Why aren't all »means« the same?

As usual: explained briefly and clearly – in under five minutes.

What considerations play a role in probability theory and what does game theory have to say in this context?

What are »AI« and »machine learning« actually? How does an algorithm recognize the difference between children and adults? And what are random forests and decision trees all about?

In this episode, we explain the basic concepts using concrete examples. We also show how data clouds and algorithms are connected.

What are »neural networks«? How are they structured? What do cats have to do with them? And how are they similar to the learning process of the human brain?

In this episode, we explain how these »artificial brains« work and how machines learn to master complex tasks with the help of neurons.

What is »Shallow Learning«? And what is behind this concept?

In this episode, we shed light on how insufficient training data and historical biases affect the performance of AI systems. We also present concrete examples to illustrate this, such as UNESCO, space travel and the Microsoft chatbot »Tay«.