Schedule

The [ML-DE] Workshop features a packed schedule of keynotes, sessions, and networking opportunities.

Workshop Date

Sunday, 20th of October 2024, Full Day

Location

Santiago de Compostela, Spain, ECAI 2024, School of Philology Room D08 Vigo

Conference Timetable

9:00-9:10 Opening Remarks

9:10-9:40 Keynote by Eunika Mercier-Laurent

Incorporation Of Expert-Knowledge Into AI Given By Differential Equations For Model Safety And Transparency

9:40-10:30 Session 1: Knowledge Infusion and Extraction

  • 9:40-10:00 EMILY: Extracting sparse Model from ImpLicit dYnamics
  • 10:00-10:20 PINNtegrate: PINN-based Integral-Learning for Variational and Interface Problems
  • 10:20-10:30 Physical knowledge improves prediction of EM Fields

10:30-11:00 Coffee Break

11:00-12:30 Session 2: Applications of Differential Equations

  • 11:00-11:20 Neural-based models ensemble for identification of the vibrating beam system
  • 11:20-11:40 A Neural Ordinary Differential Equations Approach for 2D Flow Properties Analysis of Hydraulic Structures
  • 11:40-12:00 Concept and solution of digital twin based on a Stieltjes differential equation. Application to the population dynamics of Vespa Velutina
  • 12:00-12:20 Optimal Control of a Coastal Ecosystem Through Neural Ordinary Differential Equations
  • 12:20-12:30 Graph Neural Networks and Differential Equations: A hybrid approach for data assimilation of fluid flows

12:30-14:00 Lunch Break

14:00-14:30 Keynote by Joseph Bakarji

Discovering Physically Meaningful Quantities Of Interest And Their Associated Governing Equations From Data

14:30-15:30 Session 3: Memory in Neural Differential Equations

  • 14:30-14:50 Tracing Footprints: Neural Networks Meet Non-integer Order Differential Equations For Modelling Systems with Memory
  • 14:50-15:10 Optimising Neural Fractional Differential Equations for Performance and Efficiency
  • 15:10-15:30 Time and State Dependent Neural Delay Differential Equations

15:30-16:00 Coffee Break and Poster Session

16:00-17:30 Session 4: Energy Optimization and Computational Cost Reduction

  • 16:00-16:30 Featured Presentation by Gülgün Kayakutlu: Energy-Efficient Algorithms Aiming To Reduce The Computational Footprint Of AI And Traditional Numerical Methods For Solving Differential Equations
  • 16:30-16:50 Accelerating Hopfield Network Dynamics: Beyond Synchronous Updates and Forward Euler
  • 16:50-17:10 What happens to diffusion model likelihood when your model is conditional?

17:10-17:25 Demo session / Interactive Session

17:25-17:30 Closing Remarks