Conferences  >  Mathematics  >  Neural Networks and Artificial Intelligence, Machine Learning  >  Canada

The 1st Workshop on Pragmatic Reasoning in Language Models (PragLM) aims to stimulate research on LLMs as pragmatically competent language users. We invite contributions that will forward the discussion of understanding and improvement of LLMs' capability to generate natural language flexibly and efficiently across contexts, with relations to research on the cognitive and linguistic processes supporting effective, context-sensitive communication. Our interdisciplinary theme brings together researchers in NLP, computational pragmatics, cognitive science, and other fields.

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

The High-dimensional Learning Dynamics (HiLD) workshop aims to advance our understanding of machine learning in the context of high-dimensional data, which is increasingly common as models and datasets grow in size. The workshop focuses on developing insights into how these machine learning algorithms behave in complex, high-dimensional settings, such as deep neural networks and large language models. By bringing together researchers from diverse fields, this workshop aims to develop both practical and theoretical strategies for more efficient and effective training of large-scale machine learning models. This research is critical as it can lead to better-informed decisions in model design and training, ultimately improving computational efficiency and outcomes in AI.

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

In addition to exploring new methodologies, the workshop will address key challenges such as the explainability and interpretability of decisions, data privacy, and the practical deployment of models using contextual information. While these challenges are well-recognized in the ML community, particularly with the rise of large language models, they remain underexplored in the Operations Research community. By fostering collaboration and knowledge exchange, the workshop aims to develop scalable models, promote better benchmarking practices, and expand the applicability of contextual optimization to a wider range of real-world problems.

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

DANGER is a conference at the forefront of data science for mathematics, bringing together leading academics in mathematics to discuss and share how AI methods can accelerate their research, and be used to uncover new connections and conjectures. With a focus on number theory and geometry, datasets like sequences of numbers, or lists of shapes can be quickly generated in bulk and fed into these advanced algorithms for analysis. DANGER aims to foster new collaborations across mathematical fields connected by data science, and motivate the responsible use of AI in research to advance the field.

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

The landscape of drug design is rapidly evolving, with computational methods and artificial intelligence (AI) playing an increasingly important role. This workshop aims to explore cutting-edge mathematical approaches that are transforming the field of computational drug design. We will delve into multiscale modeling techniques that bridge the gap between molecular and macroscopic levels, providing a comprehensive understanding of drug interactions and dynamics. Additionally, we will highlight the integration of generative AI and machine learning (ML) algorithms in predicting drug efficacy, optimizing molecular structure, speeding up drug repurposing, understanding potential toxicity, and thus accelerating the drug discovery and development process. By bringing together diverse experts from academia, industry, and innovation support organizations, and adding early career researchers to the mix, this workshop will foster interdisciplinary collaboration and innovation. Participants will gain insights into the latest developments, discuss challenges, and explore future opportunities in the quest for more effective and efficient drug design.

Applied Mathematics (in general),    Pharmacology and Drug Development

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

Recently a variety of state-of-the-art methods in machine learning and artificial intelligence have been developed motivated by techniques from Stein’s method, a successful tool from the field of probability theory. These methods have enabled efficient analysis of the large amounts of data being produced in several scientific fields, like neuroscience, information technology, and finance. Motivated by this success, there has been an ever increasing interest in exploring further connections between Stein’s method and machine learning. The focus of this workshop is to consolidate isolated efforts and develop a theoretically principled inferential and computational framework via Stein's method for analyzing increasingly complex models and data objects. This workshop is intended to bring together prominent and promising young and diverse researchers working on Stein’s method and machine learning, and to charter the path for future development in the field.

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

Particle physics, astrophysics, and cosmology cover the study of the universe from its smallest to largest scales. We study them in order to understand both the fundamental interactions that govern the universe and its large-scale structure and history. Advanced detectors at collider facilities that accelerate particles to near the speed of light and telescopes that monitor the night's sky looking back to the time just after the Big Bang are used to collect vast amounts of data in complicated datasets. Analyzing these data requires modern tools, making use of advanced machine learning and high performance computing infrastructure. This workshop brings together physicists, statisticians, and machine learning experts in order to make the most use of this data and learn as much from it as possible by discussing how to address the complexities of these large and detailed datasets, searching for 1 in a trillion events, and understanding correlations between thousands of quantities.

Mathematical Physics,    Probability and Statistics, Game Theory

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

Catastrophic events, even though they happen rarely, have a significant impact when they occur. Disastrous climate, financial, insurance or complex network failure events can have devastating social and environmental consequences. A complete risk analysis for modelling and prediction purposes requires understanding how these extreme, rare events occur, and what are the main drivers causing them. Machine learning methods open the road for methodological developments to forecast these extreme events and discover their complex, possibly high-dimensional nature. The aim of this workshop is to bring together researchers contributing to closely related, but culturally disconnected research communities: extreme value theory and machine learning. The goal is to discuss new directions and open mathematical problems, and foster further collaboration. The leading experts will introduce young researchers, postdocs and graduate students to the state-of-the-art in the field.

Probability and Statistics, Game Theory,    Applied Mathematics (in general)

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

This workshop brings together leading experts in neuroscience, cosmology, and AI to develop new methods that not only help us understand the universe but also the neurons that make such understanding possible. With a focus on AI (XAI), participants will create algorithms that provide new insights on complex data by revealing how and why they make decisions. By studying the neurons that help us think and the AI that explains how it "thinks," we are not just pushing the boundaries of science—we are unraveling the very mechanisms that allow us to comprehend our place in the cosmos.

Banff International Research Station for Mathematical Innovation and Discovery (BIRS)

Representation learning is at the heart of a paradigm shift in machine learning, driving many of today’s most advanced artificial intelligence (AI) systems. Representation learning transforms raw data into meaningful features that machines can use to perform a wide range of tasks, such as image recognition, content recommendation, and text generation. However, a key challenge remains: ensuring that these representations are identifiable, a property that is fundamental to reliably deploying AI systems in real-world applications. Although identifiability is critical to developing trustworthy AI systems, the current mathematical understanding of representation learning in general, and identifiability in particular, is extremely limited. To address this gap in understanding, Banff International Research Station will host a workshop focusing on principled approaches for learning identifiable representations and understanding the properties of such representations.