# The Neocognitron

Date: April 1980 · Era: W1 · The first winter · Category: theory · Significance: 4/5
People: Kunihiko Fukushima
Organisations: NHK Science and Technology Research Laboratories

Canonical: https://shapeofintelligence.com/timeline/1980-neocognitron/ · Dataset and text CC BY 4.0

> Fukushima's layered network of local feature detectors and pooling recognises patterns regardless of position, the architecture of the convolutional network.

## What had to happen

3 events back to 1943, oldest first. Direct influences are marked *direct*.

- [1943 · A logical calculus of nervous activity](https://shapeofintelligence.com/md/timeline/1943-mcculloch-pitts-neuron/)
- [1949 · Cells that fire together wire together](https://shapeofintelligence.com/md/timeline/1949-hebb-organization-of-behavior/)
- [1958 · The perceptron learns](https://shapeofintelligence.com/md/timeline/1958-perceptron/) *direct*

In 1959 Hubel and Wiesel had found that the cat's visual cortex is built from simple cells, which respond to an edge at one position and orientation, and complex cells, which respond to the same edge anywhere in a small region. Kunihiko Fukushima, working at the Japanese broadcaster NHK's research laboratory, turned that finding into a network. The Neocognitron, published in April 1980, alternates layers of S-cells that detect local features with C-cells that pool over position, stacked several times so that later layers respond to larger and more abstract patterns.

The result recognised handwritten digits regardless of where they were drawn, which a perceptron could not do. The architecture is the convolutional network: shared local filters, pooling, and depth. What the Neocognitron lacked was a good way to train it; Fukushima used an unsupervised, layer-by-layer rule.

Yann LeCun supplied the missing piece in 1989 by training the same structure with backpropagation, and AlexNet in 2012 was the Neocognitron with rectified units, dropout and two GPUs. Fukushima published in the depth of the first winter, in a journal of biology, and the field took thirty years to notice how much he had given it.

## What it led to

74 events downstream, through 2026.

Built on it directly:

- [1989 · LeNet reads handwritten postcodes](https://shapeofintelligence.com/md/timeline/1989-lenet/)

And, through them, by era:

- III · Statistics and data: 2 events
- IV · Deep learning: 10 events
- V · Transformers: 18 events
- VI · Everyone: 29 events
- VII · Agents: 14 events

## Sources

- [Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position (Biological Cybernetics, 1980)](https://doi.org/10.1007/BF00344251) — paper

---

The Shape of Intelligence by Jamie McKaye (https://jamiemckaye.com) · Markdown mirror of https://shapeofintelligence.com/timeline/1980-neocognitron/

Before: [1980 · XCON goes into production at DEC](https://shapeofintelligence.com/md/timeline/1980-xcon/) · After: [1980 · Symbolics and the Lisp machine business](https://shapeofintelligence.com/md/timeline/1980-symbolics-lisp-machines/)
