Introduction
DRAW combines a variational autoencoder, recurrent networks and differentiable attention, generating images through successive operations that read from and write to a canvas. Although it does not become the dominant architecture of later products, it demonstrates an early combination of attention and iterative image generation.
View full image ↗Page 1 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.
Karol Gregor; Ivo Danihelka; Alex Graves; Danilo Rezende; Daan Wierstra · original paper · Image rights remain with their respective holders; no open licence is asserted
Source · DRAW ↗RESEARCH ACCOUNT
Constructing an image through successive acts
ANTI-AI ARCHIVE · Revised 2026-10-02
Method and contribution
DRAW combines spatial attention with a sequential variational auto-encoding framework to construct images iteratively. Its authors explain attention through an analogy with visual fixation and evaluate results on digit-image datasets. The analogy describes a computational design, not a complete reproduction of human vision or drawing.
Section sources: DRAW
Art-historical interpretation
Editorial interpretation: generation acquires a temporal structure rather than an instantaneous result. This permits comparisons with incremental composition and revision, without assigning human intention or emotion to each computational step.
Section sources: DRAW
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 Auto-Encoding Variational Bayes.
Compare the methods, forms of control or presentation contexts of this entry and Denoising Diffusion Probabilistic Models.
Dates & version record
Date displayed for this node: 2015 · Historical date recorded for the source: 2015
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.
Provenance, translation & verification
Timeline entry #085 · Historical node
Research materials & supplement references · 1
AI Art Genealogy Research Master · p. 16 · 050
Date as recorded: 2015
DRAW ↗
DRAW
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. DRAW. Art-history node #085. https://salondesrefuses.cn/en/art-history/050
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.