Math4ML Workshop
About the workshop
Machine Learning (ML) has motivated a lot of new research in mathematics. This research uses tools from both pure and applied mathematics. The workshop will showcase some of the recent mathematical research motivated by problems coming from ML and some of the mathematical developments leveraging tools from machine learning to improve scientific discovery and engineering applications.
These include but are not limited to
PINNs (a neural networks method for numerically solving differential equations)
Optimization for ML (local vs global minima, convergence of SGD, IP and MIP formulations of deep neural networks, robust optimization, …)
Recent developments in Statistical Learning ( generalization, over-parameterization, …)
Probabilistic approaches (Bayesian ML, transfer learning, …)
Graph theory and related topics (Knowledge graphs, Graph Neural Networks, ...)
Equation Learning (symbolic regression)
Topological data analysis
Workshop Aims
The main goal of this workshop is to showcase the mathematical research around ML to the Deep Learning Indaba community but especially to the mathematicians in the community. This will hopefully inspire young African mathematicians to consider working on some of these problems. The long-term expected outcome is to grow the research community around the topics discussed in the workshop, which currently has few African members of the community.
Speakers
Plenary Talks:
Sophie Dabo (University of Lille and INRIA , France)
Rachel Ward (Microsoft, United States)
Invited Speakers:
Yaé U. Gaba (Quantum Leap Africa, Rwanda)
Kossi Amouzouvi (ScaDS.AI at Technische Universität Dresden, Germany)
Gabin Maxime Nguegnang (RWTH Aachen University, Germany)
Schedule
For details on titles and abstracts, see our book of abstracts.
Check out the full Deep Learning Indaba program here.
Organizers
Issa Karambal (Quantum Leap Africa, Rwanda)
Bubacarr Bah (Medical Research Council Unit at the London School of Hygiene & Tropical Medicine, The Gambia)
Stephen Moore (University of Cape Coast, Ghana)
Franca Hoffmann (California Institute of Technology, United States)
The organizers are grateful to the California Institute of Technology for financial support towards accommodation and travel costs for some of the speakers and participants. They also thank DeepMind for the additional tickets allowing one of the organizers and a speaker to participate in the workshop
Location and Contact
University of Ghana
CEDI Conference Center
Seminar Room 3
For any further information contact
Stephen Moore (stephen.moore@ucc.edu.gh)
Issa Karambal (ikarambal@quantumleapafrica.org)
Bubacarr Bah (Bubacarr.Bah1@lshtm.ac.uk)
Franca Hoffmann (franca.hoffmann@caltech.edu)