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

2022/11/07 by Michael J. Smith, J. E. Geach, James E. Geach · 1 voice · 3 citations
Computer Science · Engineering · Physics and Astronomy · #Anomaly Detection Techniques and Applications #Astronomical Observations and Instrumentation #Time Series Analysis and Forecasting #astro-ph.IM #cs.LG

paper · pdf · doi:10.1098/rsos.221454

arxiv published 2022/11/07 · openalex publication_date 2023/05/01 · arxiv updated 2023/05/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/16

Abstract

In this review, we explore the historical development and future prospects of artificial intelligence (AI) and deep learning in astronomy. We trace the evolution of connectionism in astronomy through its three waves, from the early use of multilayer perceptrons, to the rise of convolutional and recurrent neural networks, and finally to the current era of unsupervised and generative deep learning methods. With the exponential growth of astronomical data, deep learning techniques offer an unprecedented opportunity to uncover valuable insights and tackle previously intractable problems. As we enter the anticipated fourth wave of astronomical connectionism, we argue for the adoption of GPT-like foundation models fine-tuned for astronomical applications. Such models could harness the wealth of high-quality, multimodal astronomical data to serve state-of-the-art downstream tasks. To keep pace with advancements driven by Big Tech, we propose a collaborative, open-source approach within the astronomy community to develop and maintain these foundation models, fostering a symbiotic relationship between AI and astronomy that capitalizes on the unique strengths of both fields.

Citations

• I.—COMPUTING MACHINERY AND INTELLIGENCE
• The perceptron: A probabilistic model for information storage and organization in the brain.
• A Sociological Study of the Official History of the Perceptrons Controversy
• Finding Structure in Time
• Backpropagation Applied to Handwritten Zip Code Recognition
• Polynomial Theory of Complex Systems
• Overview of the DESI Legacy Imaging Surveys
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Momentum Contrast for Unsupervised Visual Representation Learning
• Deep Learning for Anomaly Detection
• Deep Learning for Anomaly Detection: A Review
• Highly accurate protein structure prediction with AlphaFold
• Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model
• Global Carbon Budget 2021
• The Turing Trap: The Promise & Peril of Human-Like Artificial Intelligence
• High-Resolution Image Synthesis with Latent Diffusion Models
• GPTs are GPTs: Labor market impact potential of LLMs

Cited by

• Galaxy Model Subtraction with a Convolutional Denoising Autoencoder
• The Platonic Universe: Do Foundation Models See the Same Sky?
• Applications of machine learning in gravitational-wave research with current interferometric detectors

Discussions

• Astronomia ex machina: a history, primer and outlook on neural nets in astronomy [hn, 3 points, 1 comments]

Related

• Applications of AI in Astronomy
• Deep Learning in Astrophysics
• Deep Learning for Astrophysics: An Open Textbook from the NASA Cosmic Origins AI/ML Science and Technology Interest Group
• Deeper Learning in Astronomy
• Introduction of Machine Learning for Astronomy (Hands-on Workshop)