Data Science and AI in Mathematics Education
Numerous problems and issues in today's society are so complex and the data to be processed is often so large that they can no longer be solved without the use of computers. Nowadays, methods from the field of artificial intelligence (AI) and data science (DS) are often used to solve problems based on large amounts of data. Exemplary applications can be found in the field of speech recognition (e.g. with Alexa and Siri), in autonomous driving or in the allocation of loans in private and corporate everyday life. The rapidly advancing digitalization requires that students are also familiarized with the topic of DS and AI at an early stage.
Within the framework of CAMMP / Simulated Worlds, learning material on various issues is being developed and tested, which allows students to gain an active insight into the significance of mathematics for AI methods. More specifically, the following topics have been and are currently being worked on:
Word Predictions
The generation of word suggestions, which are given to the user when composing text messages, is addressed. For this purpose, a one-day workshop was created, which is designed in such a way that students independently develop a procedure to give word suggestions on the basis of occurrence frequencies of different word sequences. The focus is on the development of the statistical language model necessary for word prediction, which is used as the prediction model. In this model, the probabilities for different word sequences are empirically determined from the training corpus. To predict the next word after a word sequence, a Markov model is used, treating each word as a state. The resulting language model is called an N-gram model in the research field of Natural Language Processing. Running the modeling process several times and combining individual N-gram models using fallback strategies or interpolation improves the prediction model.
Contact: Stephanie Hofmann
Recommender Systems and the Netflix Prize
Description follows.
Contact: Sarah Schönbrodt
Image classification
Description follows.
Contact: Sarah Schönbrodt
Handout for teachers
Currently, a contribution on the topics of word suggestions and recommendation system is being developed in a handout for teachers with sample topics for science-oriented seminar courses at schools in Baden-Württemberg. It will briefly explain the scientific background and give an overview of further questions and literature suitable for students.