[R] Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy

Author here -- here is a review paper that we have been working on for a while, was hoping to get a little discussion going on it!

In it we survey deep learning within astronomy, and identify three historical waves. We plot astronomical connectionism's course from the early days of training multilayer perceptrons on expertly derived emergent parameters, through the second wave of training recurrent and convolutional neural networks on raw data, and the third wave of self-supervised, unsupervised and …

astronomy history machinelearning networks neural networks