Deep learning· 1980
Neocognitron: A Self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position
On the reading lists
- #440 in the Top 500 (2026 edition)
- #50 in Deep learning (2026 edition)
Why it matters
Introduced hierarchical visual feature extraction with alternating cell types, anticipating convolutional architectures.
Condensed from the expert lists' notes.
The record
- First released
- 1980 (from OpenAlex)
- Citations
- 5,724 citations, as counted by OpenAlex (CC0)
- Named by
- both expert lists
- Also relevant to
- Computer vision & multimodal
- Score
- 0.365 · computed rank 440 · consensus 0.7, must-read 0.5, citations percentile 0.3 (1980s · deep-learning), awards 0, existing lists 0. Method
Editor's notes
- Readability check: pass: The ancestor of convolutional networks; readable. (AI draft (Claude), not yet reviewed, 2026-10-29)
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.