The event has passed

AI for Scientific Data Analysis: Mini-conference

This event will provide researchers and industry professionals a unique opportunity to learn about how the latest advancements in artificial intelligence are being used to enhance scientific data analysis.


The event has passed
Registration (Opens in new tab)

The mini-conference will feature a diverse range of speakers from both academia and industry, who will present their cutting-edge research and share their insights on the current state of the field. There will also be ample time to network with fellow professionals.

Some of the topics that will be covered include:

  • Machine learning algorithms for complex data analysis
  • Applications of deep learning in scientific research
  • Real-world examples of AI in action in various scientific fields
  • Tools and techniques for incorporating AI into data analysis workflows

Whether you are a researcher or data analyst using AI, or simply someone interested in the intersection of AI and scientific data analysis, this mini-conference is for you. The event is free of charge.


31 May

9:20-9:30: Welcome by the organizers
9:30-10:15: Daniel Freedman; Molecular Design via Semi-Equivariant Normalizing Flows
10:15-10:30: Yu-Wei Chang; Training of neural networks with incomplete datasets
10:30-10:45: Caroline Adiels; Dynamic virtual live/apoptotic/dead cell assay using deep learning
10:45-11:00: Agnese Callegari; Faster and More Accurate Geometrical-Optics Optical Force Calculation Using Neural Networks
11:00-11:15: Mattias Geilhufe; AI design of organic quantum matter using the Organic Materials Database
11:15-12:00: Balpreet Singh Ahluwalia; Development of high-throughput on-chip optical nanoscopy and label-free quantitative phase microscopy for life science


14:00 -14:15: Adel Daoud; The AI and Global Development Lab
14:15-14:30: Smaragda-Maria Argyri ; Acoustic levitation and machine learning for the determination of surface properties
14:30-14:45: Edoardo Grasso; Discovering far astrophysical sources: a bizarre application of generative models
14:45-15:00: Viktor Martvall; Deep Ensemble Modelling for Acceleration of Nanoplasmonic Gas Sensing
15:00-15:15: Valentina Matovic; Revealing the complex nano porous structure of a polymer hybrid electrolyte aided by deep learning


15:45-16:00: Greger Hammarin; Classification of diffraction patterns in single particle X-ray experiments
16:00-16:15: Christopher Kolloff; Resolving Disparities between Experiments and Simulations of Biomolecular Systems using Dynamic Augmented Markov Models
16:15-17:00: Ramin Bostanabad; Materials design under multiple coexisting uncertainties
17:00-- Light dinner & Posters

1 June

9:20-9:30: Welcome again (by the organizers)
9:30-10:15: Elias Nehme; Towards intelligent microscopes with deep learned optics
10:15-10:30: Jesús Pineda; Geometric deep learning reveals the spatiotemporal features of microscopic motion
10:30-10:45: Basudev Roy; Towards detection of pitch rotation in birefringent microspheres from video microscopy
10:45-11:00: Henrik Klein Moberg; Deep Learning Microscopy for label-free sub-10 kDa molecule characterization
11:00-11:45: Lars Tornberg; Evaluation of generative models for cytometry applications in drug development


13:45-14:30: Carlo Manzo; Data-driven approaches for the analysis of molecular motion
14:30-14:45: Joel Jonsson; Towards efficient large-scale microscopy image analysis using content-adaptive deep learning
14:45-15:00: Daniel Midtvedt ; Optical characterization of biological matter across scales
15:00-15:15: Harshith Bachimanchi; Microplankton life histories revealed by holographic microscopy and deep learning
15:15-15:30: Benjamin Midtvedt; Single-shot self-supervised object detection in microscopy


16:00-16:45: Cynthia Rudin; Scoring systems: at the extreme of interpretable machine learning
16:45—Light dinner & Posters

External speakers; titles and abstracts


AI for Scientific Data Analysis

This theme is about utilizing the power of AI as a tool for scientific research. AI can be applied to, and potentially speed up, discovery and utilization in a variety of research disciplines, such as microscopy, physics, biology, chemistry, and astronomy.


Henrik Klein Moberg
  • Doctoral Student, Chemical Physics, Physics