Machine Learning in Support of Computational and Theoretical Sciences:
Knowledge Discovery in Time Series Data
Date & Venue:
Tuesday, 6 December 2022 | Breakaway Room | Wallenberg Conference Centre | STIAS
Machine learning techniques play an increasing role in assisting scientists and engineers in knowledge discovery: obtaining novel information from large, possibly complex data sets. Many practically important tasks, such as weather prediction, financial forecasting, or speech processing, are modelled using time series information. Knowledge discovery in time series data is an active field of research, with techniques such as feature attribution used to gain new insights into the underlying processes being modelled.
This workshop provides a forum for discussion and brainstorming ideas related to knowledge discovery in time series data. It is supported by the National Institute for Theoretical and Computational Sciences (NITheCS).
We aim to bring together interested researchers who work in this field (whether NITheCS associates or other interested parties) to share their recent findings and views. Work in progress is welcomed. Topics of interest include but are not limited to:
- Applications of time series modelling
- Interpretability techniques
- Knowledge discovery from data
Call for abstracts:
Submissions are invited from researchers on the above topics. Abstracts will be reviewed for relevance and interest. Full papers will not be required prior to the workshop. Rather, it is envisaged that the workshop’s outcomes will form the seed for future joint publications.
Abstract submission: 3 October (early) and 14 November (late breaking)
Notification of acceptance: 17 October (early) and 29 November (late breaking)
Final programme made available: 31 November
Workshop: 6 December
Note that there are two submission/notification dates: An early date for authors who require confirmation of acceptance in advance, and a second submission date for late breaking results.
Authors wishing to both submit a full paper for review and participate in this workshop, should follow the standard SACAIR process for full paper submission. Such authors are invited to submit the same abstract here, for discussion in a workshop format.
Please send your submissions to: email@example.com
Preliminary workshop programme:
|08:00 – 08:30||Welcome & Introduction||Marelie Davel & Stefan Lotz|
|08:30 – 10:00||Presentations (according to abstracts received)||To be confirmed|
|10:30 – 12:00||Presentations (continued)||To be confirmed||12:00 – 13:00||Lunch||All||13:00 – 15:00||Discussion: review & way forward||Panel discussion||15:00 – 15:30||Closure||Francesco Petruccione|
More information on the NITheCS research programme:
‘Knowledge Discovery in Time Series Data’ is a project within the machine learning research programme of NITheCS.
The overall programme has two main aims:
- Machine learning research: development of new, specialised machine learning techniques.
- Machine learning as tool: applying machine learning for scientific modelling applications.
In addition, the programme aims to grow a forum for cross-cutting projects executed in other NITheCS focus areas, where those projects rely on machine learning expertise.
- Marelie Davel (NWU)
- Stefan Lotz (SANSA)