Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
The DOI matches its Crossref record; 12 of the 13 references it cites were found in a registry or an index.
Abstract
A neural network model for a mechanism of visual pattern recognition is proposed in this paper. The network is self-organized by "learning without a teacher", and acquires an ability to recognize stimulus patterns based on the geometrical similarity (Gestalt) of their shapes without affected by their positions. This network is given a nickname "neocognitron". After completion of self-organization, the network has a structure similar to the hierarchy model of the visual nervous system proposed by Hubel and Wiesel. The network consists of an input layer (photoreceptor array) followed by a cascade connection of a number of modular structures, each of which is composed of two layers of cells connected in a cascade. The first layer of each module consists of "S-cells", which show characteristics similar to simple cells or lower order hypercomplex cells, and the second layer consists of "C-cells" similar to complex cells or higher order hypercomplex cells. The afferent synapses to each S-cell have plasticity and are modifiable. The network has an ability of unsupervised learning: We do not need any "teacher" during the process of self-organization, and it is only needed to present a set of stimulus patterns repeatedly to the input layer of the network. The network has been simulated on a digital computer. After repetitive presentation of a set of stimulus patterns, each stimulus pattern has become to elicit an output only from one of the C-cells of the last layer, and conversely, t…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Beyond the single-unit design discussed here, artificial neural networks were inspired by another seemingly universal design principle associated with cortical architecture [255]: the presence of multiple processing layers (such as those found in the visual cortex).”
From Fundamental constraints to the logic of living systems (2024) · cites this paper as [255]
In the citing paper
“Convolutional neural networks (CNNs) constitute one such class of models.9,15,17,19,21,26,32”
From ImageNet classification with deep convolutional neural networks (2017) · cites this paper as [9]
In the citing paper
“In the early 1980s, three new classes of NNs emerged, namely Convolutional Neural Network (CNN) [157], Self-Organizing Map (SOM) [249], and Hopfield network [195].”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [157]
Citations
Cites
Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex
Hubel, D. H., & Wiesel, T. N. (1962) · The Journal of Physiology · doi:10.1113/jphysiol.1962.sp006837 · Cited by 13,680
Ferrier lecture. Functional architecture of macaque monkey visual cortex
Hubel, D. H., & Wiesel, T. N. (1977) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1977.0085 · Cited by 2,608
RECEPTIVE FIELDS AND FUNCTIONAL ARCHITECTURE IN TWO NONSTRIATE VISUAL AREAS (18 AND 19) OF THE CAT
Hubel, D. H., & Wiesel, T. N. (1965) · Journal of Neurophysiology · doi:10.1152/jn.1965.28.2.229 · Cited by 2,603
Mullin, A. A., & Rosenblatt, F. (1963) · The American Mathematical Monthly · doi:10.2307/2312103 · Cited by 2,209
Visual properties of neurons in inferotemporal cortex of the Macaque.
Gross, C. G., Rocha-Miranda, C. E., & Bender, D. B. (1972) · Journal of Neurophysiology · doi:10.1152/jn.1972.35.1.96 · Cited by 1,483 · cited 1×
“), and their responses are scarcely affected by the position or the size of the stimuli (Gross et al., 1972; Sato et al., 1978).”
BackgroundCognitron: A self-organizing multilayered neural network
Fukushima, K. (1975) · Biological Cybernetics · doi:10.1007/bf00342633 · Cited by 757
Self-citationde la Tour, E. B., Bolle, A., & Kellenberger, E. (2008) · Pathologia et Microbiologia · doi:10.1159/000161635 · Cited by 147
A Proposed Model for Visual Information Processing in the Human Brain
Snider, R. S. (1967) · Neurology · doi:10.1212/wnl.17.6.625 · Cited by 52
A Proposed Model for Visual Information Processing in the Human Brain
Kabrisky, M. (1966) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign) · Cited by 44
Feature Extraction and Recognition of Handwritten Characters by Homogeneous Layers
Giebel, H. (1971) · Springer eBooks · doi:10.1007/978-3-642-65175-5_15 · Cited by 13
Research works printed but not linked: 4
- Fukushima, K.: Improvement in pattern-selectivity of a cognitron (in Japanese). Pap. Tech. Group MBE78-27, IECE Japan (1978)
- Fukushima, K.: Self-organization of a neural network which gives position-invariant response. In: Proceedings of the Sixth International Joint Conference on Artificial Intelligence. Tokyo, August 20?23, 1979, pp. 291?293 (1979b)
- Fukushima, K.: Improvement in pattern-selectivity of a cognitron (in Japanese). Trans. IECE Japan (A), J 62-A, 650?657 (1979c)
- Meyer, R.L., Sperry, R.W.: Explanatory models for neuroplasticity in retinotectral connections. In: Plasticity and function in the central nervous system. Stein, D.G., Rosen, J.J., Butters, N. (eds.), pp. 45?63. New York, San Francisco, London: Academic Press 1974
Cited by
Items 1,001–1,028 of 1,028
van den Noort, F., van der Vaart, C. H., Grob, A. T. M., van de Waarsenburg, M. K., Slump, C. H., & van Stralen, M. (2019) · Ultrasound in Obstetrics & Gynecology · doi:10.1002/uog.20181 · Cited by 52
“The TPUS images of 40 subjects were selected randomly (test set 2, TS2) and the PRM and UH were segmented manually at rest, on contraction and on Valsalva, following the same procedure as that used for the first data set.”
BackgroundMethodCNN architecture comparison for radio galaxy classification
Becker, B., Vaccari, M., Prescott, M., & Grobler, T. (2021) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stab325 · Cited by 50
“This inspired theNeocognitron artificial neural network (Fukushima 1980) which combined layers consisting wholly of one of two types of “cells” into a hierarchicalmodel to perform handwritten character recognition.”
MethodWhere are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Majumdar, A., Yadav, K., Arnaud, S., Ma, Y. J., Chen, C., Silwal, S., Jain, A., Berges, V.-P., Abbeel, P., Malik, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.18240 · Cited by 49
“In this work, we ask the same question that Fukushima [1, 2] asked nearly 50 years ago – how do we design an artificial visual cortex , the module in a computational system that (together with a policy) enables an agent to convert camera input into actions?”
BackgroundWhere are we in the search for an artificial visual cortex for embodied intelligence
Majumdar, A., Yadav, K., Arnaud, S., Ma, J., Chen, C., Silwal, S., Jain, A., Berges, V.-P., Wu, T., Vakil, J., et al. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-0031 · Cited by 49
Zhang, C., Wang, X., Zhang, H., Zhang, H., & Han, P. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3125967 · Cited by 49
Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks
Giusti, A., Cireşan, D. C., Masci, J., Gambardella, L. M., & Schmidhuber, J. (2013) · arXiv · doi:10.48550/arxiv.1302.1700 · Cited by 48
Fritz, B. A., Chen, Y., Murray-Torres, T. M., Gregory, S., Ben Abdallah, A., Kronzer, A., McKinnon, S. L., Budelier, T., Helsten, D. L., Wildes, T. S., et al. (2018) · BMJ Open · doi:10.1136/bmjopen-2017-020124 · Cited by 42
“Deep learning methods, especially those using convolutional neural networks (CNNs), 37 have achieved great success in learning useful representations (features) from images.”
MethodLearning and disrupting invariance in visual recognition with a temporal association rule
Isik, L., Leibo, J. Z., & Poggio, T. (2012) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2012.00037 · Cited by 38
Computer Vision-Based Wood Identification: A Review
Silva, J., Bordalo, R., Pissarra, J., & de Palacios, P. (2022) · Forests · doi:10.3390/f13122041 · Cited by 37
Fundamental constraints to the logic of living systems
Solé, R., Kempes, C. P., Corominas-Murtra, B., De Domenico, M., Kolchinsky, A., Lachmann, M., Libby, E., Saavedra, S., Smith, E., & Wolpert, D. (2024) · Interface Focus · doi:10.1098/rsfs.2024.0010 · Cited by 34
“Beyond the single-unit design discussed here, artificial neural networks were inspired by another seemingly universal design principle associated with cortical architecture [255]: the presence of multiple processing layers (such as those found in the visual cortex).”
Background(1993) · Cited by 29
Karamitrou, A., Sturt, F., Bogiatzis, P., & Beresford-Jones, D. (2022) · Surface Topography: Metrology and Properties · doi:10.1088/2051-672x/ac9492 · Cited by 29
“This new technology was largely based on the seminal work of Fukushima (1980) as well as Hubel and Wiesel (1959) that introduced the ‘neocognitron’ (Fukushima 1980; 1983; 2003) and established the use of convolutional and down-sampling layers.”
MethodNakhle, F., & Harfouche, A. L. (2021) · Patterns · doi:10.1016/j.patter.2021.100323 · Cited by 28
“It was capable of analyzing images 57,58 and led to the birth of deep convolutional neural networks (DCNNs).”
BackgroundDeep Predictive Learning: A Comprehensive Model of Three Visual Streams
O'Reilly, R. C., Wyatte, D. R., & Rohrlich, J. (2017) · arXiv · doi:10.48550/arxiv.1709.04654 · Cited by 26
“Then, we do not require a canonical object representation, but rather rely on well-established principles of hierarchical topographic connectivity to develop invariant object representations in the high levels of the What pathway (Fukushima, 1980; Riesenhuber & Poggio, 1999; O’Reilly et al., 2013).”
MethodConvolutional Neural Networks for the Identification of African Lions from Individual Vocalizations
Trapanotto, M., Nanni, L., Brahnam, S., & Guo, X. (2022) · Journal of Imaging · doi:10.3390/jimaging8040096 · Cited by 24
“Although it was first developed in the 1980s [38], interest in CNN snowballed after it achieved outstanding results in the ImageNet Large Scale Visual Recognition Challenge, where a GPU-based CNN won the competition [39].”
BackgroundMachine learning at the edge for AI-enabled multiplexed pathogen detection
Ganjalizadeh, V., Meena, G. G., Stott, M. A., Hawkins, A. R., & Schmidt, H. (2023) · Scientific Reports · doi:10.1038/s41598-023-31694-6 · Cited by 24
CoNNa–Hardware accelerator for compressed convolutional neural networks
Struharik, R. J. R., Vukobratović, B. Z., Erdeljan, A. M., & Rakanović, D. M. (2020) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2020.102991 · Cited by 18
Thorn, A. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102368 · Cited by 16
Matsumoto, T., Walston, S. L., Walston, M., Kabata, D., Miki, Y., Shiba, M., & Ueda, D. (2022) · Journal of Digital Imaging · doi:10.1007/s10278-022-00691-y · Cited by 15
The changing fortunes of pattern recognition and computer vision
Chellappa, R. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.04.005 · Cited by 8
“More information on these developments can be found in [9-13].”
BackgroundDo More Dropouts in Pool5 Feature Maps for Better Object Detection
Shen, Z., & Xue, X. (2014) · arXiv · doi:10.48550/arxiv.1409.6911 · Cited by 7
“CNNs were firstly introduced in 1980 by Kuni-hiko Fukushima [14] For a parameter-trained network, correspondence between pool 5 features and concepts of each channel would also be fixed, such as shape, texture and material properties.”
MethodShigeno, S. (2017) · Diversity and Commonality in Animals · doi:10.1007/978-4-431-56469-0_19 · Cited by 6
KINNTREX: a neural network to unveil protein mechanisms from time-resolved X-ray crystallography
Biener, G., Malla, T. N., Schwander, P., & Schmidt, M. (2024) · IUCrJ · doi:10.1107/s2052252524002392 · Cited by 6
Design and evaluation of a global workspace agent embodied in a realistic multimodal environment
Dossa, R. F. J., Arulkumaran, K., Juliani, A., Sasai, S., & Kanai, R. (2024) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2024.1352685 · Cited by 5
“While neuroscience had a profound influence on the fields of artificial neural networks (ANNs) and deep learning (DL) in the past (Rosenblatt, 1962; Fukushima, 1980; Rumelhart et al., 1986; LeCun and Bengio, 1995), in recent years the direction of influence has largely changed, and deep neural networks…”
BackgroundModern Machine Learning Methods for Time Series Analysis
Huang, C., & Petukhina, A. (2022) · Statistics and Computing · doi:10.1007/978-3-031-13584-2_10 · Cited by 2
Nested Learning: The Illusion of Deep Learning Architectures
Behrouz, A., Razaviyayn, M., Zhong, P., & Mirrokni, V. (2025) · arXiv · doi:10.48550/arxiv.2512.24695 · Cited by 37
“Another common building block is a convolutional layer (Fukushima, 1980; LeCun et al., 1989).”
BackgroundSingle-neuron encoding of rapidly learned visual information reshapes human perception
Armendariz, M., Blumberg, J., Singer, J., Aiple, F., Kim, J., Domínguez-Iturza, N., Brandt, A., Reinacher, P., Schulze-Bonhage, A., & Kreiman, G. (2026) · Nature Neuroscience · doi:10.1038/s41593-026-02496-6
“The main family of models to describe visual recognition capabilities is based on hierarchical deep neural networks 1–6 .”
Metadata
- Authors
- Fukushima, K.
- Affiliations
- Japan Broadcasting Corporation (Japan) (JP)
- Corresponding author
- Fukushima, Kunihiko
- ORCID
- Fukushima, Kunihiko
- Venue
- Biological Cybernetics
- Published
- 1980-04
- Volume
- 36
- Issue
- 4
- Pages
- 193-202
- ISSN
- 0340-1200 (ISSN-L)
- 1432-0770
- OpenAlex
- W613766092
- Semantic Scholar
- 69e68bfaadf2dccff800158749f5a50fe82d173b
- Cited by
- 5,759
- References
- 13
- Citations by year
- 2026: 219 · 2025: 454 · 2024: 494 · 2023: 455 · 2022: 452 · 2021: 544 · 2020: 545 · 2019: 433 · 2018: 301 · 2017: 319 · 2016: 287 · 2015: 176 · 2014: 140 · 2013: 78 · 2012: 71
- FWCI
- 4.02
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Biological Cybernetics (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Life Sciences › Neuroscience › Cognitive Neuroscience › Visual perception and processing mechanisms
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
- Keywords
- neocognitron, visual pattern recognition, unsupervised learning, self-organization, position invariance, S cells, C cells, simple cells, complex cells, hypercomplex cells, visual cortex model, synaptic plasticity, shape recognition
- MeSH terms
- Cognition, Computers, Form Perception, Learning, Models, Neurological, Nerve Net, Nervous System Physiological Phenomena, Pattern Recognition, Visual
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.