Konferenzen  >  Informatik  >  Implementierung und Anwendungen von künstlicher Intelligenz  >  Kanada

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)

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.