Welcome to the 2024 workshop hosted by the CHAIR theme Structured learning, which is held for the second year. This is a 3 days lunch-to-lunch event with international and local speakers.
Overview
- Date:Starts 29 October 2024, 12:00Ends 31 October 2024, 12:00
- Seats available:100
- Location:A Working Lab, Chalmers Campus Johanneberg
- Language:English
In this workshop we broadly cover topics related to Structured Learning, targeting specifically the following questions:
- How can we encode structure (e.g., scientific domain knowledge) into learning systems?
- How does domain knowledge affect uncertainty quantification and out-of-distribution predictions?
- Can these insights enable us to solve problems in a data and computationally-efficient manner? We will have a particular focus on inverse and surrogate modeling.
- How can these strategies help scientific discovery?
Event page with registration and full information
The workshop consists of four sessions spread over 3 days:
- Data efficiency and generalization
- Uncertainty quantification
- Inverse problems
- Applications
The workshop is free to attend but requires registration. The event includes free coffee breaks and lunches. Please register early as capacity is very limited!
The event is organized by the CHAIR theme on Structured Learning: Rocío Mercado (CSE), Moritz Schauer (MATH), Axel Ringh (MATH), and Simon Olsson (CSE).
Structured learning
This theme focuses on how to make use of structure in data to build machine learning (ML) and artificial intelligence (AI) systems which are safer, more trustworthy and generalize better. Structure includes the relationship between data, in time and space, and how the predictions change when data is transformed in specific ways, for example rotated or scaled. These topics are abstract and general but have a direct impact on the use of AI and ML in the sciences and in applications such as drugs and materials design, or medical imaging.
