Efficient and Reliable Deep Learning Methods and their Scientific Applications (25w5382)

The Banff International Research Station will host the “Efficient and Reliable Deep Learning Methods and their Scientific Applications” workshop in Banff from June 22 - 27, 2025.

Deep learning brings unprecedented opportunities to solve scientific challenges such as accelerating scientific computing, modeling infectious disease spreading and climate change, discovering new drugs/materials, and providing smart/mobile healthcare. Artificial Intelligence (AI) coupled with scientific computing methods will play a key role. Though recent progress in AI has been driven empirically to a large extent by big data and high computational costs, we aim to address efficiency, reliability and interpretability which are critical issues in applications.

The workshop will explore mathematical principles and algorithms for efficient and reliable deep learning and their scientific applications, most notably techniques based on low precision, sparsification, low rank, symmetry, fast integral transforms, efficient neural architectural search and multi-level knowledge distillation. Applications include fast computation of multi-scale and parameterized partial differential equations in several space dimensions, long-range interaction modeling and multi-modal deep learning in physical, biological and health sciences. The workshop aims to bring together a diverse spectrum of computational scientists across multiple disciplines at various stages of their careers to foster broad interactions and develop new ideas to advance the field.

The Banff International Research Station for Mathematical Innovation and Discovery (BIRS) is a collaborative Canada-US-Mexico venture that provides an environment for creative interaction as well as the exchange of ideas, knowledge, and methods within the Mathematical Sciences, with related disciplines and with industry. The research station is located at The Banff Centre in Alberta and is supported by Canada’s Natural Science and Engineering Research Council (NSERC), the U.S. National Science Foundation (NSF), and Alberta’s Advanced Education and Technology.