Machine Learning in Astronomy

This theme is grounded in research on Machine Learning to model the human visual system and making systems that can recreate human visual classification performance. For the last 7 years the focus has been on ML applied to astronomical data to, amongst other things, finding Lensed Galaxies, improving angular resolution on Wide-field (but blurry) Extragalactic Surveys and to untangle the vast amounts of data for Ice Astrochemistry.

Key publications

• Using Convolutional Neural Networks to identify Gravitational Lenses in Astronomical images
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Using cGANs for Anomaly Detection: Identifying Astronomical Anomalies in JWST Imaging
• Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks
• Signature verification using a "Siamese" time delay neural network