Neocognitron
Kunihiko Fukushima published Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position in Biological Cybernetics in April 1980. The paper proposes a self-organizing neural-network model for visual pattern recognition and explicitly gives the network the nickname neocognitron.
Historical classification
This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.
Why it matters
A documented historical neural-network milestone describing a hierarchical self-organizing pattern-recognition architecture before later convolutional-network developments.
People, organizations & technologies
PEOPLE
Kunihiko Fukushima
ORGANIZATIONS
NHK Broadcasting Science Research Laboratories
TECHNOLOGIES
Neocognitron, Self-organizing neural network, Pattern recognition
Evidence & verification
STATE
verified
CONFIDENCE
high
LAST VERIFIED
2026-09-12T01:04:38+08:00
Springer Nature's publisher record directly supports the title, author, Biological Cybernetics placement, April 1980 publication and issue month, pages 193-202, DOI 10.1007/BF00344251, and Fukushima's affiliation with NHK Broadcasting Science Research Laboratories. The abstract describes a self-organizing visual-pattern-recognition network explicitly nicknamed the neocognitron. PubMed independently corroborates the article identity and bibliographic details. Month precision is retained; the affiliation is recorded as author affiliation only, not as inferred development or release geography. No ancestry, influence, causality, or relationships are inferred.
Sources
Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
Springer Nature / Biological Cybernetics
Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
PubMed / U.S. National Library of Medicine
Trace the chronology
Record identity
LINEAiGE IDneocognitron-1980