Introduction
GANs organize generation through learning data distributions. In contrast with a rule-based system such as AARON, the logic producing an image is learned from training data rather than mainly being specified by an artist. The master identifies a change in how machine images are understood: outputs are treated as samples from a learned distribution.
View full image ↗Page 4 of the linked paper PDF, preserving its original figures and language. The source file identifies the edition; later revision or reprint dates do not replace the node’s historical date.
Goodfellow et al. · original paper · Image rights remain with their respective holders; no open licence is asserted
Source · Generative Adversarial Nets ↗RESEARCH ACCOUNT
Learning to generate through an adversarial task
ANTI-AI ARCHIVE · Revised 2026-10-02
Method and contribution
GANs train a generator and discriminator together. One produces samples; the other distinguishes generated samples from training data. The generator improves through the discriminator’s errors. The paper combines an idealised game-theoretic result with neural-network experiments. Its equilibrium analysis is not a guarantee that every practical training run succeeds.
Section sources: Generative Adversarial Nets
Art-historical interpretation
Editorial interpretation: generation and evaluation are linked during training, but the discriminator is not an art critic. Artistic practice also involves dataset choice, training, selection and display. Belamy and Klingemann’s installations allow the algorithm’s publication to be distinguished from its subsequent institutional uses.
Section sources: Generative Adversarial Nets
Sources for this account
Author or conference abstract and version record read; full proofs and experiments were not independently reproduced.
This account expands the archive within the cited scope. Historical interpretation is not presented as the original author’s statement or as a proven causal influence. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Compare the methods, forms of control or presentation contexts of this entry and Portrait of Edmond de Belamy.
Compare the methods, forms of control or presentation contexts of this entry and Memories of Passersby I.
Dates & version record
Date displayed for this node: 2014 · Historical date recorded for the source: 2014
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
Generative Adversarial Nets
https://papers.nips.cc/paper/5423-generative-adversarial-nets
Current cited URL
Provenance, translation & verification
Timeline entry #080 · Historical node
Research materials & supplement references · 1
AI Art Genealogy Research Master · p. 15 · 045
Date as recorded: 2014
Generative Adversarial Nets ↗
Generative Adversarial Nets
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
The master’s research claims and dates await independent verification.
Cite this node
ANTI-AI ARCHIVE. Generative Adversarial Nets. Art-history node #080. https://salondesrefuses.cn/en/art-history/045
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.