Machine Learning Open House

Come to our meetup to learn how we create enterprise-grade, human-centric AI solutions. We will cover topics such as Deep Learning for digital pathology, Natural Language Processing for question answering, and the challenge of ethical, sustainable AI in general.

Design Thinking in AI projects - Avoid solving the wrong problem
Many AI systems fail because they ignore the larger context of their application. We will discuss how design thinking helps to avoid this, by not trying to solve a given problem with AI directly, but restructure it in a way that leads to an optimal end-to-end flow of human and AI based activities.
Speakers: M. Wurst and team
PoDBAY - statistical modeling of vaccine efficacy
Vaccine clinical trials can be long and costly with an uncertain outcomes. We will discuss an innovative statistical approach to predict vaccine efficacy, recently developed and published by MSD.
Speaker: K. Zelinková
Atlas registration of mice, 3D light sheet microscopy data processing
Drugs for neurodegenerative diseases are often studied in mouse brains. An important part of tissue image processing is the annotation of individual brain regions. We have developed a machine learning-based pipeline that can automate this activity using atlas registration.
Speaker: M. Vagenknecht
3D light-sheet image data analysis drives drug development. It allows to focus the analysis on the entire organs and not just a small subset of the tissue. We will discuss how to build a tailored statistical pipeline, which includes machine learning and deep learning components, for automated analysis of costume readouts.
Speaker: P. Hrobař

Responsible and Ethical AI
The application of AI methods brings many benefits across fields, however, we should be aware of possible pitfalls whether it comes from biased data, misused application, or lack of oversight. This is particularly important in areas with a direct impact on people's lives. MSD approach will be discussed at the end of the presentation.
Speaker: P. Vácha