Word prediction and what it has to do with math!

Artificial intelligences have long been involved as Alexa and Siri or in autonomous driving, and AI also supports us when chatting with friends: We get words suggested and thus not only save valuable time, but also make fewer mistakes when writing. But how does the cell phone know what I want to write next? How can such word suggestions be generated, in such a way that they are highly likely to deliver the word the user wants to write? How well do such word suggestions work? Is it even possible to use such predictive models to imitate the user's speech so well that no one notices that the text is generated by an AI instead of a real human?

In this workshop, students will create a prediction model themselves, improve it, and test it. In the process, the practical relevance of mathematics in everyday life becomes apparent and the students experience a completely new action-oriented computer-based approach to mathematics.

Duration: from 4 hours
Contents: stochastics (concept of probability), markov chains (transition graphs and tables), optimization
Previous knowledge: relative and absolute frequency, concept of probability
Participants: Mathematics courses from grade 9 onwards
Created by: Stephanie Hofmann
Registration: Appointments can be made individually by e-mail at KIT or RWTH Aachen University.

Source of image: https://unsplash.com/photos/ik_AuIWeBBM