COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Data Intensive Science Seminar Series > Polymathic AI: Foundation Models for Science
Polymathic AI: Foundation Models for ScienceAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact James Fergusson. n the last few years, natural language processing and computer vision have experienced a fundamental shift in the way these fields use machine learning. Rather than training neural networks from a randomly initialized set of parameters, researchers have often found superior performance can be achieved by fine-tuning a general pre-trained “foundation model” trained on vast amounts of diverse data – perhaps because this model comes with better “priors” than an untrained network. Polymathic AI1 is a new research collaboration that aims to usher in the same shift in machine learning for scientific datasets. In this talk I will present the motivations behind the collaboration and describe the findings of our three new papers in this space, which examine: better numerical encodings for large language models2, contrastive embeddings for multi-modal scientific data3, and building machine learning models that learn from multiple types of physics4. 1 https://polymathic-ai.org/ 2https://arxiv.org/abs/2310.02989 3https://arxiv.org/abs/2310.03024 4https://arxiv.org/abs/2310.02994 This talk is part of the Data Intensive Science Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsComputer Vision Reading Group @ CUED Engineering Department Geotechnical Research Seminars CamBridgeSensOther talks“Unexpected physiologic role of alpha-synuclein Serine-129 phosphorylation” Mathematical driver model with a Gaussian Process internal model to represent learning behaviour CANCELLED: Rafal Szabla on Quantum Chemical Perspective on the Prebiotic Origins of RNA and DNA Wine Production and Exchange in Late Antique Egyptian Monasteries: A Micro-Economic Analysis’ Two emergent biophysical phenomena motivated by Turing and Jeffery Plasmodesmata Cell Walls |