Contrastive Learning and High-Redshift Quasars

Add to your list(s) Download to your calendar using vCal

• Xander Byrne
• Wednesday 21 February 2024, 14:00-15:00
• Maxwell Centre.

If you have a question about this talk, please contact Sri Aitken.

The basic task of unsupervised machine learning is to cluster similar data together. Contrastive learning [Chen+20] has emerged as a popular clustering algorithm, with the referenced paper garnering over a thousand citations since the method’s inception at Google at the start of this decade. It is based on a familiar concept ported from the field of supervised learning – data augmentation, the expansion of a training set by adding innocuous transformations of training data, such as rotations of an image. Contrastive learning is fuelled by data augmentation, teaching a network to ignore such trivial changes, improving generalisability whilst it learns to cluster. This talk will give an overview of contrastive learning, data augmentation, and some examples where it has been used effectively, including the discovery of three unique high-redshift quasars

This talk is part of the Data Intensive Science Seminar Series series.

This talk is included in these lists:

• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Combined External Astrophysics Talks DAMTP
• Cosmology, Astrophysics and General Relativity
• Institute of Astronomy Extra Talks
• Institute of Astronomy Talk Lists
• Interested Talks
• Maxwell Centre
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.