Registration is closed!

Program

18.30  Opening remarks

18.45  Artificial intelligence for leukemia diagnostics - Carsten Marr (Helmholtz Institute of AI for Health)

19.15  Artificial intelligence in Chemical Data Analysis, Catalyst Design and Kinetic Analysis - Oliver Trapp (Faculty for Chemistry and Pharmacy at the LMU Munich)

19.45  short break

19.55  Self-organisation of intelligent agents - from biology to robotics - Steffen Rulands (Arnold Sommerfeld Center for Theoretical Physics)

20.25  Discussion between the invited guests: AI in life sciences

20.45  Questions from participants 

 

Abstracts

Carsten Marr: Artificial intelligence for leukemia diagnostics

Diagnosing blood diseases still relies on the subjective visual assessment of images by cytologists and pathologists. These experts are confronted with an ever increasing amount of data sets, rare diagnostic cells, and heterogeneous disease manifestations. Despite available patient data, deep learning algorithms, and our profound knowledge on how the blood system works, there is currently no model to automatically analyze and predict disease dynamics from a blood smear or bone marrow puncture.

In my talk, I will discuss the tremendous progress in computer vision and artificial intelligence to address this biomedical challenge at the interface of digital pathology, machine learning, computer vision, and mathematical modelling.

Oliver Trapp: Artificial intelligence in Chemical Data Analysis, Catalyst Design and Kinetic Analysis

Artificial neural networks were already used relatively early in chemistry, e.g. for the evaluation of spectra and structural analysis. New algorithms and the available computing power of modern computers open up completely new possibilities of use in the field of data analysis, structural analysis and especially in the field of catalysis research.Catalytic processes are typically optimised by comprehensive screening of catalysts, substrates, reaction parameters and additives to enhance activity and selectivity. The common problem of the multidimensionality of the parameter space, leading to only incremental improvement in laborious physical investigations. This can be overcome by combining elements from machine learning, optimisation and experimental design as demonstrated in this presentation. Another exciting field is the use of AI in the quantitative kinetic analysis of complex reaction networks.

Steffen Rulands: Self-organisation of intelligent agents - from biology to robotics

Self-organisation, where complex behaviour emerges from the collective interactions of many components, is a fundamental principle underlying many phenomena in physics, biology and chemistry. In the examples of societies of complex organisms or interacting robots these components themselves possess the ability to sense and react to complex cues. In this talk, I will discuss how we use statistical physics to understand self-organisation in matter consisting of such intelligent agents.

 

This event is organized by the JungChemiker Forum Munich (JCF Munich), the Junior German Society for Biochemistry and Molecular Biology (jGBM) and the young DPG (jDPG).