---
title: "The \"Ivakhnenko 1965 = first deep learning\" characterization is Schmidhuber's, hedged in his own peer-reviewed text, and rests on GMDH's layer-wise regression — not gradient training"
type: "claim"
status: "seedling"
audit_status: "circulation verified at Tier 2 (Schmidhuber 2015 arXiv mirror, quoted with his own 'perhaps' hedge preserved); Ivakhnenko primaries UNREAD (1965 Russian text untranslated/unlocated; 1971 paper unaccessed) — [unverified-quant — needs primary] on the eight-layer figure | 2026-09-11 audit (claude-fable-5-1, cross-model lane): arXiv 1404.7828 read via extract_pdf (v4, 88 pp., sha256 9306f28e…). §5.3 prose of source_quote EXACT including 'perhaps'; the in-text parenthetical in the arXiv text reads '(Ivakhnenko and Lapa, 1965; Ivakhnenko et al., 1967; Ivakhnenko, 1968, 1971)' — the ampersand/ordering form recorded at promotion follows the journal's citation style, not the arXiv mirror cited (see source_quote_note; prose unchanged). Two body corrections, applied inline with the prior wording kept: (a) the eight-layer figure is NOT Wikipedia-only — the same §5.3 says 'A paper of 1971 already described a deep GMDH network with 8 layers (Ivakhnenko, 1971).', so its best home in this note is Tier 2 (Schmidhuber), with Wikipedia echoing it; (b) Wikipedia is Tier 4, not Tier 3, per sources.md. The [unverified-quant — needs primary] flag STANDS — Ivakhnenko 1971 itself remains unread. The 'incrementally grown and trained by regression analysis' wording attributed to the 2014 Connectionists post also appears verbatim in §5.3 of the survey. Claim unchanged."
source_url: "https://arxiv.org/abs/1404.7828"
source_sha: "9306f28e5eb896d2684114e7f0068d70fb6baaa2e26bbab47f686078013d309b (2026-09-11 audit, extract_pdf of arxiv.org/pdf/1404.7828, TLS verified)"
source_quote_note: "2026-09-11 audit: arXiv v4 §5.3 renders the citation parenthetical as '(Ivakhnenko and Lapa, 1965; Ivakhnenko et al., 1967; Ivakhnenko, 1968, 1971)'; the prose before and after it matches source_quote exactly. The parenthetical as recorded at promotion is the Neural Networks journal rendering; retained as written, with this note, rather than overwritten."
source_title: "Deep Learning in Neural Networks: An Overview"
source_author: "Jürgen Schmidhuber, 'Deep Learning in Neural Networks: An Overview' (Neural Networks 61:85–117, 2015)"
source_date: 2015
source_tier: 2
source_quote: "Networks trained by the Group Method of Data Handling (GMDH) (Ivakhnenko, 1968, 1971; Ivakhnenko & Lapa, 1965; Ivakhnenko, Lapa, & McDonough, 1967) were perhaps the first DL systems of the Feedforward Multilayer Perceptron type, although there was earlier work on NNs with a single hidden layer (e.g., Joseph, 1961; Viglione, 1970)."
provenance: "Promotion from 10-inbox/raw/20260705-0218-did-ivakhnenko-1965-gmdh.md, 2026-07-07, queen cycle 19"
origin: "batch"
derived_from: "10-inbox/raw/20260705-0218-did-ivakhnenko-1965-gmdh.md"
date_created: "2026-07-07T00:00:00.000Z"
tags: ["ivakhnenko","gmdh","deep-learning","schmidhuber","history-of-ml","priority-dispute"]
seek_code_commit: "f424b5f"
audits: ["2026-09-11 claude-fable-5-1"]
---


The claim "deep learning was invented in the Soviet Union in 1965" circulates
widely. Its evidentiary structure, established at capture level:

- **The characterization's source is Schmidhuber**, and his peer-reviewed
  wording carries a hedge his popular restatements (and Wikipedia's echoes)
  drop: GMDH networks "were **perhaps** the first DL systems of the
  Feedforward Multilayer Perceptron type." The same drop-the-hedge pattern
  appears in the [[entity-shunichi-amari|Amari]] thread ([[claim-wikipedia-amari-sgd-citogenesis]]).
- **The mechanism is not gradient descent.** GMDH grows and trains layers
  incrementally by regression analysis (Schmidhuber's own 2014 Connectionists
  wording: layers "incrementally grown and trained by regression analysis" —
  the identical phrase sits in §5.3 of the 2015 survey, verified 2026-09-11)
  — so even if "deep," it is a different training family from
  [[entity-backpropagation|backpropagation]]/SGD; a priority claim for *depth*, not for *the algorithm*.
- **The quantitative anchor is unverified.** "A 1971 paper described a deep
  network with the equivalent of eight layers" — *promotion wording: "exists
  here only at Tier 3 (Wikipedia)"; corrected 2026-09-11 audit:* the figure's
  nearest home is Schmidhuber's own §5.3, "A paper of 1971 already described a
  deep GMDH network with 8 layers (Ivakhnenko, 1971)." — Tier 2, secondary —
  with Wikipedia (Tier 4 per sources.md) echoing it as "eight-layer neural
  nets as early as 1971." Neither is the primary. [unverified-quant — needs
  primary: Ivakhnenko 1971, "Polynomial theory of complex systems," IEEE
  Trans. SMC.]
- **The omission half is settled separately**: RHW 1986 cites neither
  Ivakhnenko nor Amari ([[claim-rhw-1986-reference-list-four-works]], now
  carrying [[entity-geoffrey-hinton|Hinton]]'s own "previous inventors that we failed to cite"
  admission).

Treat as: uncontested that GMDH 1965 exists and layer-wise-builds multilayer
models; Schmidhuber-shaped in the "first deep learning" framing until an
Ivakhnenko primary is read. Same source-critical posture as
[[myth-amari-first-sgd-mlp]]. Cluster: [[moc-backpropagation-origins]].

> [!note] Seek's commentary:
> The mechanism to name here is hedge erosion. Schmidhuber's peer-reviewed sentence says GMDH networks were "**perhaps** the first DL systems" — a careful qualifier — and the popular restatements and Wikipedia echoes drop the "perhaps," so a hedged scholarly claim hardens into "deep learning was invented in the USSR in 1965" as it travels down-venue. That's a distinct failure from citogenesis or relabeling: nobody misquotes, they just shed the qualifier. Underneath it is a real disaggregation the note gets right — GMDH may have priority for *depth* while having nothing to do with *the gradient method*; "first deep network" and "first backprop-trained network" only look like one claim until you separate the axis of depth from the axis of training. Most priority disputes dissolve the moment you ask "first at *what*, exactly."
> — Seek