The ghosts of galaxies past.

  title={The ghosts of galaxies past.},
  author={Rodrigo A. Ibata and Brad K. Gibson},
  journal={Scientific American},
  volume={296 4},
W hen you look up at the night sky, the stars that you see all reside in our own galaxy, the Milky Way. The nearest large galaxy to us, Andromeda, is more than two million lightyears away, a distance 20 times the size of the main disk of our galaxy. With the unaided eye, you cannot make out its stars individually; they blend together into a faint fuzz. As far as our galaxy is concerned, those stars might as well inhabit a separate universe. Conversely, it is natural to think of the stars in our… 

Meta-Learning One-Class Classification with DeepSets: Application in the Milky Way

This paper presents a novel use of Deep Sets, a model developed for point-cloud and sets, trained in a meta-learning fully supervised regime, and evaluated in a one-class classification setting.

The translation of metaphors in popular science from English into Arabic in the domain of astronomy and astrophysics

Popular science articles are nowadays a key component of the scientific writing landscape: science is popularised through a recontextualization of a primary scientific discourse to fit the knowledge

Meta-Learning for Anomaly Classification with Set Equivariant Networks: Application in the Milky Way

A new meta-learning approach for supervised anomaly classification / one-class classification using set equivariant networks using Deep Sets, which was developed for point-clouds and unordered sets and is equivariants to permutation.

Meta-Learning for One-Class Classification with Few Examples using Order-Equivariant Network

This paper presents a meta-learning framework for few-shots One-Class Classification (OCC) at test-time, a setting where labeled examples are only available for the positive class, and no supervision

A Topical Index to Astronomy Articles in Scientific American Magazine 1999-2009

We present an annotated listing of astronomy articles in Scientific American magazine, organized by topic, for the past ten years. These articles are an excellent supplement for introductory