Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Bowles, Micah"'
Autor:
Walmsley, Mike, Bowles, Micah, Scaife, Anna M. M., Makechemu, Jason Shingirai, Gordon, Alexander J., Ferguson, Annette M. N., Mann, Robert G., Pearson, James, Popp, Jürgen J., Bovy, Jo, Speagle, Josh, Dickinson, Hugh, Fortson, Lucy, Géron, Tobias, Kruk, Sandor, Lintott, Chris J., Mantha, Kameswara, Mohan, Devina, O'Ryan, David, Slijepevic, Inigo V.
We present the first systematic investigation of supervised scaling laws outside of an ImageNet-like context - on images of galaxies. We use 840k galaxy images and over 100M annotations by Galaxy Zoo volunteers, comparable in scale to Imagenet-1K. We
Externí odkaz:
http://arxiv.org/abs/2404.02973
Autor:
Slijepcevic, Inigo V., Scaife, Anna M. M., Walmsley, Mike, Bowles, Micah, Wong, O. Ivy, Shabala, Stanislav S., White, Sarah V.
In this work, we apply self-supervised learning with instance differentiation to learn a robust, multi-purpose representation for image analysis of resolved extragalactic continuum images. We train a multi-use model which compresses our unlabelled da
Externí odkaz:
http://arxiv.org/abs/2305.16127
Autor:
Bowles, Micah, Tang, Hongming, Vardoulaki, Eleni, Alexander, Emma L., Luo, Yan, Rudnick, Lawrence, Walmsley, Mike, Porter, Fiona, Scaife, Anna M. M., Slijepcevic, Inigo Val, Adams, Elizabeth A. K., Drabent, Alexander, Dugdale, Thomas, Gürkan, Gülay, Hopkins, Andrew M., Jimenez-Andrade, Eric F., Leahy, Denis A., Norris, Ray P., Rahman, Syed Faisal ur, Ouyang, Xichang, Segal, Gary, Shabala, Stanislav S., Wong, O. Ivy
We present a novel natural language processing (NLP) approach to deriving plain English descriptors for science cases otherwise restricted by obfuscating technical terminology. We address the limitations of common radio galaxy morphology classificati
Externí odkaz:
http://arxiv.org/abs/2304.07171
Autor:
Bowles, Micah, Tang, Hongming, Vardoulaki, Eleni, Alexander, Emma L., Luo, Yan, Rudnick, Lawrence, Walmsley, Mike, Porter, Fiona, Scaife, Anna M. M., Slijepcevic, Inigo Val, Segal, Gary
We define deriving semantic class targets as a novel multi-modal task. By doing so, we aim to improve classification schemes in the physical sciences which can be severely abstracted and obfuscating. We address this task for upcoming radio astronomy
Externí odkaz:
http://arxiv.org/abs/2210.14760
Unknown class distributions in unlabelled astrophysical training data have previously been shown to detrimentally affect model performance due to dataset shift between training and validation sets. For radio galaxy classification, we demonstrate in t
Externí odkaz:
http://arxiv.org/abs/2207.08666
New astronomical tasks are often related to earlier tasks for which labels have already been collected. We adapt the contrastive framework BYOL to leverage those labels as a pretraining task while also enforcing augmentation invariance. For large-sca
Externí odkaz:
http://arxiv.org/abs/2206.11927
Autor:
Cárcamo, Miguel, Scaife, Anna, Taylor, Russ, Jarvis, Matt, Bowles, Micah, Sekhar, Srikrishna, Heino, Lennart, Stil, Jeroen
In this work we present a novel compute framework for reconstructing Faraday depth signals from noisy and incomplete spectro-polarimetric radio datasets. This framework is based on a compressed-sensing approach that addresses a number of outstanding
Externí odkaz:
http://arxiv.org/abs/2206.03283
Autor:
Slijepcevic, Inigo V., Scaife, Anna M. M., Walmsley, Mike, Bowles, Micah, Wong, Ivy, Shabala, Stanislav S., Tang, Hongming
In this work we examine the classification accuracy and robustness of a state-of-the-art semi-supervised learning (SSL) algorithm applied to the morphological classification of radio galaxies. We test if SSL with fewer labels can achieve test accurac
Externí odkaz:
http://arxiv.org/abs/2204.08816
In this work we use variational inference to quantify the degree of uncertainty in deep learning model predictions of radio galaxy classification. We show that the level of model posterior variance for individual test samples is correlated with human
Externí odkaz:
http://arxiv.org/abs/2201.01203
In this work we introduce group-equivariant self-attention models to address the problem of explainable radio galaxy classification in astronomy. We evaluate various orders of both cyclic and dihedral equivariance, and show that including equivarianc
Externí odkaz:
http://arxiv.org/abs/2111.04742