Throughout the year, HIDA and the six Data Science Schools invite outstanding international Data Scientists to speak about their current research in the HIDA Lectures.
Energy, Earth and Environment, Health, Information, Matter, as well as Aeronautics, Space and Transport - The HIDA Lectures cover a wide range of topics and offer the opportunity to dive into the diversity of current approaches in Data Science.
We cordially invite the interested public to attend these lectures and especially doctoral researchers from the Helmholtz Association. Discuss with international researchers about different application fields of Data Science and gain insights into the diverse activities of the Schools and HIDA.
All events of the series are open to the public.
Watch again - past lectures
HIDA Lecture @ DASHH - Quantum Machine Learning in Chemical Compound Space
Date: April 15, 2021, 14:00
Abstract: Many of the most relevant observables of matter depend explicitly on atomistic and electronic details, rendering a first principles approach to computational materials design mandatory. Alas, even when using high-performance computers, brute force high-throughput screening of material candidates is beyond any capacity for all but the simplest systems and properties due to the combinatorial nature of compound space, i.e. all the possible combinations of compositional and structural degrees of freedom. Consequently, efficient exploration algorithms exploit implicit redundancies and correlations. I will discuss recently developed statistical learning based approaches for interpolating quantum mechanical observables throughout compound space. Numerical results indicate promising performance in terms of efficiency, accuracy, scalability and transferability.
Alan Akbik is a professor of machine learning at Humboldt University in Berlin. His research focuses on natural language processing (NLP), i.e., methods that enable machines to understand human language. This includes research topics such as transfer learning, few-shot learning, and semantic parsing, as well as application areas in large-scale text analysis. Akbik's research is operationalized in the form of the open-source NLP framework Flair, which allows anyone to use state-of-the-art NLP methods in their research or applications.
HIDA Lecture @ HEIBRiDS - TARS: Few-Shot Learning for Natural Language Processing
Date: June 16, 2021, 16:00
Abstract: Machine learning models for natural language processing (NLP) are typically trained with very large amounts of labeled training data. However, such data is often not readily available and very expensive to produce. In this talk I present TARS, a novel approach in the research area of "few-shot learning" which allows us to train text classification models with little training data - or even none at all! I show how the proposed approach can be applied to a continual learning setup in which a single model learns a number of different tasks in sequence, with the goal of learning all tasks. Finally, I give a brief overview of the Flair NLP framework (https://github.com/flairNLP/flair) we develop in my group together with the open source community, and show how you can use TARS (and other NLP components in Flair) in your own research or industry projects.