Machine learning (automated processes that learn by example in order to classify, predict, discover or generate new data) and artificial intelligence (methods by which a computer makes decisions or discoveries that would usually require human intelli
gence) are now firmly established in astronomy. Every week, new applications of machine learning and artificial intelligence are added to a growing corpus of work. Random forests, support vector machines, and neural networks (artificial, deep, and convolutional) are now having a genuine impact for applications as diverse as discovering extrasolar planets, transient objects, quasars, and gravitationally-lensed systems, forecasting solar activity, and distinguishing between signals and instrumental effects in gravitational wave astronomy. This review surveys contemporary, published literature on machine learning and artificial intelligence in astronomy and astrophysics. Applications span seven main categories of activity: classification, regression, clustering, forecasting, generation, discovery, and the development of new scientific insight. These categories form the basis of a hierarchy of maturity, as the use of machine learning and artificial intelligence emerges, progresses or becomes established.
The ability to quickly detect transient sources in optical images and trigger multi-wavelength follow up is key for the discovery of fast transients. These include events rare and difficult to detect such as kilonovae, supernova shock breakout, and o
rphan Gamma-ray Burst afterglows. We present the Mary pipeline, a (mostly) automated tool to discover transients during high-cadenced observations with the Dark Energy Camera (DECam) at CTIO. The observations are part of the Deeper Wider Faster program, a multi-facility, multi-wavelength program designed to discover fast transients, including counterparts to Fast Radio Bursts and gravitational waves. Our tests of the Mary pipeline on DECam images return a false positive rate of ~2.2% and a missed fraction of ~3.4% obtained in less than 2 minutes, which proves the pipeline to be suitable for rapid and high-quality transient searches. The pipeline can be adapted to search for transients in data obtained with imagers other than DECam.
