Astrophysics (Index)About

machine learning

(ML)
(use of programs that extract their algorithms from data)

The term machine learning (ML) is typically used for a computer technique (ML technique) in which the software first takes some given some data that includes example input with desired results and adjusts parameters such that it can produce correct results from analogous input data. The term is commonly used for such software that consists of neural networks, networks of interconnectable logical and arithmetic computations, a strategy inspired by a brain's neurons networked with synapses. (Usage of the term deep learning varies, but often it is used specifically for ML using neural networks.) With the development of such techniques and with increasing computational capacity, the method has become very effective for a number of types of applications, including recognizing patterns such as patterns within images, a common use in astronomy.


Note the abbreviation ML also is used for the probability/statistics term maximum likelihood also used in astronomy, such as in the phrase ML mapmaking.


(technique,computation)
Further reading:
https://en.wikipedia.org/wiki/Machine_learning
https://mitsloan.mit.edu/ideas-made-to-matter/machine-learning-explained
https://www.ibm.com/topics/machine-learning
https://levity.ai/blog/difference-machine-learning-deep-learning
https://indico.cern.ch/event/683620/contributions/3420614/attachments/1840352/3017035/Lab_Infieri_LabPresentation.pdf
https://ui.adsabs.harvard.edu/abs/2023RSOS...1021454S/abstract

Referenced by pages:
balanced accuracy (BA)
basis function
deep learning
mixture density network (MDN)
neural network (NN)
nonparametric model
random forest
spectral feature
SPOCK
symbolic regression
XGBoost

Index