Seminar - Statistical and Machine Learning Methods

Course Description and Goals:

Statistical learning is a field that teaches students how to analyze and interpret data by applying statistical methods and machine learning algorithms to uncover patterns, make predictions, and gain insights from data. The syllabus includes:

• Statistical and machine learning methods, including linear and polynomial regression, logistic regression, and linear discriminant analysis.

• Model validation techniques such as cross-validation and bootstrap, model selection, and regularization methods (ridge and lasso).

Spring School 2025 in Aachen – Research Data Management in Materials Science and Engineering

Enabling a consistent and unobstructed standardization of research data will lead to substantial improvements in efficiency and synergies/collaboration among individual researchers and well-designed IT systems. In the era of digital infrastructures, this measure holds paramount importance in shaping the future of research. For the data to be sustainable and reusable, it must adhere to the “FAIR Data Principles”, meaning it should be “Findable, Accessible, Interoperable, and Re-usable”. The FAIR principles will be a cornerstone of the European Open Science Cloud (EOSC) implementation. Nowadays, Data Management Plans (DMPs) have become a requirement for project applications in Horizon Europe and are increasingly being demanded by various funding organizations, including the German Science Foundation (DFG), among others. The scientific consortium NFDI-MatWerk (National Research Data Infrastructure) focuses on the research area Materials Science & Materials Engineering (MSE). The central challenge is the digital representation of materials and their relevant process and load parameters. NFDI-MatWerk will provide in this summer school tailored information and solutions for dealing with research data in MSE.

Hackathon DKZ.2RxQUADRIGA

On May 8th, the Data Literacy Centers DKZ.2R and QUADRIGA are teaming up for a hackathon on the topic of text-corrections using LLM’s.

This will be an internal event for members of the Data Literacy Centers DKZ.2R and QUADRIGA.

The Data Literacy Center QUADRIGA is primarily focused on creating high-quality educational resources for the digital humanities. In our hackathon we will work on a use casedealing with historical texts from the time of the spanish flu. Channelling our resources and competencies will not only help us to strengthen the connections between our two Data Literacy Centers but will also provide us with a use case on how to use LLMs for the post-correction of automatically recognized historical texts which can be used for training purposes such as Data Challenges and Workshops in a variety of different domains.