deep learning

Also known as DL, deep machine learning, hierarchical learning, deep structured learning

branch of machine learning

AI overview

Deep learning is a branch of machine learning that uses computer systems designed to learn from data. It matters because it enables computers to improve their performance at tasks without being explicitly programmed for each specific situation.

AI-generated from the Wikipedia summary — may contain errors.

Research

137,152 papers

A guide to deep learning in healthcare.ReviewNature medicine · 2019Esteva A, Robicquet A, Ramsundar B et al.DOI: 10.1038/s41591-018-0316-z
Deep-learning seismology.ReviewScience (New York, N.Y.) · 2022Mousavi SM, Beroza GCDOI: 10.1126/science.abm4470
Deep learning in cancer diagnosis, prognosis and treatment selection.ReviewGenome medicine · 2021Tran KA, Kondrashova O, Bradley A et al.DOI: 10.1186/s13073-021-00968-x
Explainable artificial intelligence (XAI) in deep learning-based medical image analysis.ReviewMedical image analysis · 2022van der Velden BHM, Kuijf HJ, Gilhuijs KGA et al.DOI: 10.1016/j.media.2022.102470
Deep Learning in Cardiology.ReviewIEEE reviews in biomedical engineering · 2019Bizopoulos P, Koutsouris DDOI: 10.1109/RBME.2018.2885714
Deep Learning and Geriatric Mental Health.ReviewThe American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry · 2024Aizenstein H, Moore RC, Vahia I et al.DOI: 10.1016/j.jagp.2023.11.008
Deep Learning in Image-Based Plant Phenotyping.ReviewAnnual review of plant biology · 2024Murphy KM, Ludwig E, Gutierrez J et al.DOI: 10.1146/annurev-arplant-070523-042828
Deep learning applications in protein crystallography.ReviewActa crystallographica. Section A, Foundations and advances · 2024Matinyan S, Filipcik P, Abrahams JPDOI: 10.1107/S2053273323009300

via PubMed

~40 min read

Encyclopedic overview

Representing images on multiple layers of abstraction in deep learning

In machine learning, deep learning (DL) focuses on utilizing multilayered neural networks to perform tasks such as classification, regression, and representation learning. The field takes inspiration from biological neuroscience and revolves around stacking artificial neurons into layers and "training" them to process data. The adjective "deep" refers to the use of multiple layers (ranging from three to several hundred or thousands) in the network. Methods used can be supervised, semi-supervised or unsupervised.

Excerpted from Wikipedia’s “deep learning” article, available under the CC BY-SA 4.0 licence.

deep learning

Research

Encyclopedic overview

Gallery (5)

Available in 71 languages

What links here1,336 pages

What links here1,336 pages