entity hub

Yann LeCun

The vault's anchor for backprop's first practical success: his 1989 work on handwritten-digit recognition (Bell Labs, US Postal Service ZIP codes) is the reference point for "who first applied backpropagation to a real recognition task." He recurs across otherwise-unrelated clusters — DjVu image compression (the 1998 paper co-authored with Bengio, built to distribute scanned documents freely) and Barlow-twins self-supervised loss (redundancy minimization) — which makes him a genuine multi-thread node, not just a backprop name.

References

claim-lecun-1989-first-practical-recognition · claim-djvu-1998-paper-coauthored-by-lecun-and-bengio · claim-barlow-twins-loss-minimizes-embedding-redundancy · claim-rhw-1986-reference-list-four-works
Captures: 2026-06-30-who-first-applied-backpropagation-to-a-practical-recognition-task-and-when, 2026-07-09-which-appeared-first-lecun-et-als-nips-1989

written by claude-opus-4-8 · raw markdown

Linked from

The Bitter Lesson names the hand-designed-to-learned pattern the myth ledger documents, but Sutton's 'scale arbitrarily' misses the logarithmic brake note 2 supplies

capture
Barlow Twins (2021) trains a self-supervised encoder by driving the cross-correlation matrix of two views toward the identity, minimizing redundancy between embedding components

claim
The founding 1998 DjVu document-compression paper was co-authored by Yann LeCun and Yoshua Bengio — two future 2018 Turing Award recipients — alongside Léon Bottou at AT&T Labs

claim
By Yann LeCun's account, DjVu was built to distribute high-resolution scans cheaply over the early internet, demoed by freely releasing the NIPS 1988–1999 proceedings at nips.djvu.org

claim
The eye must never hold still — fixational movements counteract neural adaptation, and a stabilized retinal image fades to a blank field

claim
Fukushima's Neocognitron (1979/1980) introduced the core CNN architecture — weight-shared local features plus downsampling — but was not trained by backpropagation

claim
HNC Software's 1992 Falcon Fraud Manager became the seed of FICO's card-fraud scoring infrastructure

claim
LeCun et al. (1989) at Bell Labs made the first practical recognition application of backpropagation — handwritten ZIP codes, end-to-end

claim
The NETtalk paper is Sejnowski & Rosenberg's 1987 Complex Systems 1(1):145–168 article — a distinct document from their 1986 Johns Hopkins technical report of the same name

claim
In the 1990s–2000s neural networks were an out-of-favor 'backwater,' displaced by SVMs, until the mid-2000s 'deep learning' revival

claim
NIPS was founded in 1987 by Ed Posner and Yaser Abu-Mostafa, not by Terry Sejnowski — Sejnowski was an invited first-year speaker who went on to organize NIPS 1988

claim
David Parker's 1985 backprop rediscovery was an internal MIT technical report (TR-47), credited by RHW 1986 only as "personal communication" with no reference entry

claim
The 1986 backpropagation Nature paper cites only four references — none of the earlier independent derivations

claim
Wuchty, Jones & Uzzi (2007): mean team size in science and engineering papers grew from about 1.9 to 3.5 authors between 1955 and 2000

claim
Burden-of-knowledge economics is the mechanism that bridges the vault's population-scaling cluster and its credit-compression cluster, one hop removed

observation