HIDA Lectures

Helmholtz Information & Data Science Academy Lectures

The HIDA Lectures are a series of events organized by HIDA together with the six Helmholtz Information & Data Science Schools. Throughout the year, the Data Science Schools invite outstanding international Data Scientists to talk about their current research.

   

Since the Schools cover all Helmholtz research areas - Energy; Earth and Environment; Health; Information; Matter; and Aeronautics, Space and Transport - the series will reflect a broad range of topics and provide a great opportunity to dive into the diversity of current approaches in Data Science.

We cordially invite the interested public to attend these talks and especially PhD researchers of the Helmholtz Association. They can gain insight into the diverse activities of the Schools and HIDA, but most importantly discuss with international researchers about different application fields of Data Science.

    

All events in the series are open to the public.

   

More info on the schools

HIDA Lectures

HIDA Lectures @ HEIBRiDS

Date: June 16 2021, 4 pm

Speaker: Alan Akbik, Humboldt-Universität zu Berlin

Title: "TARS: Few-Shot Learning for Natural Language Processing”

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.

Please register here >>

Date: 15 April 2021, 2 p.m.

Title of the lecture: "Quantum Machine Learning in Chemical Compound Space"

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.

Speaker: Anatole von Lilienfeld, Professor for "Computational Materials Discovery", Universität Wien

Von Lilienfeld's research focus is highly interdisciplinary, using physical, mathematical, and computational sciences for the quantum mechanical exploration of chemical space.

You can see a recording of the lecture here.

download