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 501–600 of 1,028
Face Space Representations in Deep Convolutional Neural Networks
O’Toole, A. J., Castillo, C. D., Parde, C. J., Hill, M. Q., & Chellappa, R. (2018) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2018.06.006 · Cited by 142
Intrusion Detection Systems: A Cross-Domain Overview
Tidjon, L. N., Frappier, M., & Mammar, A. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2922584 · Cited by 160
“…(99.81% for KDDTRain+, 68.55% for KDDTest-21) than other methods. e) Deep convolutional neural networks: A Deep Convolutional Neural Network (DCNN) [204], [205] is a deep or generalized representation of ANNs that consists of a number of convolutional and subsampling layers, followed by one or…”
BackgroundInfluentialPinto, N., Stone, Z., Zickler, T. E., & Cox, D. (2011) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2011.5981788 · Cited by 168
“These models, inspired by Fukushima’s Neocognitron [6], belong to the broader class of convolutional neural networks [12], and they have previously been used in a variety of machine vision contexts [23, 8, 9, 16, 17, 18, 19, 15].”
MethodGranular computing: from granularity optimization to multi-granularity joint problem solving
Wang, G., Yang, J., & Ji, X. (2016) · Granular Computing · doi:10.1007/s41066-016-0032-3 · Cited by 147
“In 1984, Fukushima proposed a neocognitron (Fukushima 1980) based on the concept of receptive field (Hubel and Wiesel 1962) which LW learnerK”
BackgroundInvolvement of Machine Learning for Breast Cancer Image Classification: A Survey
Nahid, A.-A., & Kong, Y. (2017) · Computational and Mathematical Methods in Medicine · doi:10.1155/2017/3781951 · Cited by 154
“Fukushima first introduced a CNN named “necognitron” which has the ability to recognize stimulus patterns with a few shifting variances [113].”
BackgroundArtificial Neural Networks and Deep Learning in the Visual Arts: a review
Santos, I., Castro, L., Rodríguez-Fernández, N., Torrente-Patiño, Á., & Carballal, A. (2021) · Neural Computing and Applications · doi:10.1007/s00521-020-05565-4 · Cited by 164
D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks
Demiray, B. Z., Sit, M., & Demir, I. (2021) · SN Computer Science · doi:10.1007/s42979-020-00442-2 · Cited by 127
“Networks goes back [83], [84], CNNs are starting to reach its true potential with the help of recent developments on modern GPUs (Graphic Processing Units).”
BackgroundAn Overview of Neural Network CompressionPreprint
O’Neill, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.03669 · Cited by 180
“We assume a basic familiarity with deep learning architectures1, namely, Recurrent Neural Networks [(RNNs) 155, 75], Convolutional Neural Networks [50] 2 and Self-Attention based networks [181]3,4.”
MethodDeep learning approach for human action recognition in infrared images
Akula, A., Shah, A. K., & Ghosh, R. (2018) · Cognitive Systems Research · doi:10.1016/j.cogsys.2018.04.002 · Cited by 145
Deep Learning for Understanding Satellite Imagery: An Experimental Survey
Mohanty, S. P., Czakon, J., Kaczmarek, K., Pyskir, A., Tarasiewicz, P., Kunwar, S., Rohrbach, J., Luo, D., Prasad, M., Fleer, S., et al. (2020) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2020.534696 · Cited by 173
“This became possible through algorithmic advances — as using recti fi ed-linear units that avoid vanishing of the gradient during training (Krizhevsky et al., 2012) — , as well as implementing convolutional and pooling layers that had originally been proposed long before (Fukushima, 1980).”
MethodMao, M., & Hong, M. (2025) · Sensors · doi:10.3390/s25072270 · Cited by 161
What Do We Understand About Convolutional Networks?Preprint
Hadji, I., & Wildes, R. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08834 · Cited by 165
Using transfer learning to detect galaxy mergers
Ackermann, S., Schawinski, K., Zhang, C., Weigel, A. K., & Turp, M. D. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty1398 · Cited by 137
“…the discovery of receptive fields of neurons in the visual cortex, and taking advantage of the translational symmetry of natural images lead researchers to experiment with this type of layer for solving visual processing tasks with ANNs (Fukushima 1980; Lecun et al. 1998; Krizhevsky et al. 2017).”
MethodYang, W., Jin, L., Tao, D., Xie, Z., & Feng, Z. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.04.007 · Cited by 151
Deep Q-Learning With Q-Matrix Transfer Learning for Novel Fire Evacuation Environment
Sharma, J., Andersen, P., Granmo, O.-C., & Goodwin, M. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.2967936 · Cited by 143
“networks [31] used in DQN [51], [52], DDQN [58], [59] and Dueling DQN [60], we implement a fully connected feedforward neural network.”
MethodYOLOv11 optimization for efficient resource utilization
Rasheed, A. F., & Zarkoosh, M. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07520-3 · Cited by 147
“The second era began with the development of convolutional neural networks (CNNs) [11, 14, 25].”
Figure-ground organization and object recognition processes: An interactive account.
Vecera, S. P., & O’Reilly, R. C. (1998) · Journal of Experimental Psychology Human Perception & Performance · doi:10.1037//0096-1523.24.2.441 · Cited by 137
Nahid, A.-A., & Kong, Y. (2018) · Information · doi:10.3390/info9010019 · Cited by 137
“Though the model “AlexNet” proposed by Krizhevsky has gained a new momentum in the CNN research field, a CNN model was first utilized by Fukushima et al. [19] who proposed the “Necognitron” model that recognises stimulus patterns.”
MethodModeling visual recognition from neurobiological constraints
Oram, M. W., & Perrett, D. I. (1994) · Neural Networks · doi:10.1016/s0893-6080(05)80153-4 · Cited by 146
Beyeler, M., Dutt, N. D., & Krichmar, J. L. (2013) · Neural Networks · doi:10.1016/j.neunet.2013.07.012 · Cited by 140
“012 ventral stream as a hierarchical feed-forward network, such as the Neocognitron (Fukushima, 1980), HMAX (Riesenhuber & Poggio, 1999), or VisNet (Rolls, 2012; Wallis & Rolls, 1997)—although it should be noted that the notion of a strictly hierarchical or feedforward network has been questioned by recent anatomical…”
BackgroundCompressing Convolutional Neural Networks in the Frequency Domain
Chen, W., Wilson, J., Tyree, S., Weinberger, K. Q., & Chen, Y. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939839 · Cited by 127
“Although CNNs have been known for a quarter of a century [17], only recently have their superb generalization abilities been accepted widely across the machine learning and computer vision communities.”
BackgroundFrom handcrafted to learned representations for human action recognition: A survey
Zhu, F., Shao, L., Xie, J., & Fang, Y. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.06.007 · Cited by 148
Automatic Detection of Depression in Speech Using Ensemble Convolutional Neural Networks
Vázquez-Romero, A., & Gallardo-Antolín, A. (2020) · Entropy · doi:10.3390/e22060688 · Cited by 156
“CNNs appeared in 1980s [34], but the research that became a milestone was [35] where a CNN-based net was proposed for image recognition tasks.”
BackgroundNeural network architectures for robotic applications
King, S. Y., & Hwang, J. (1989) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.88082 · Cited by 143
Human and artificial cognition
Siemens, G., Marmolejo-Ramos, F., Gabriel, F., Medeiros, K., Marrone, R., Joksimovic, S., & de Laat, M. (2022) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2022.100107 · Cited by 133
Finding strong lenses in CFHTLS using convolutional neural networks
Jacobs, C., Glazebrook, K., Collett, T., More, A., & McCarthy, C. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx1492 · Cited by 133
“In recent years the field of computer vision has been revolutionized by advancements in deep learning techniques, in particular the use of convolutional neural networks (“ConvNets” - Fukushima (1980); Lecun et al. (1998)).”
Pixel-wise regression using U-Net and its application on pansharpening
Yao, W., Zeng, Z., Lian, C., & Tang, H. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.103 · Cited by 133
“As one of the most import deep learning model that has achieved the most widespread and successful applications in recent years, the structure of convolutional neural networks is to some extent a simulation of animals visual nervous system (Fukushima, 1980).”
BackgroundSpectral-spatial classification of hyperspectral image using autoencoders
Lin, Z., Chen, Y., Zhao, X., & Wang, G. (2013) · International Conference on Information, Communications & Signal Processing (ICICS) · doi:10.1109/icics.2013.6782778 · Cited by 156
“The layer-wise training framework has a bunch of alternatives like Restricted Boltzmann Machines [15], Pooling Units [16], Convolutional Neural Networks [17] and Autoencoders [13].”
MethodLung nodule detection in CT images using deep convolutional neural networks
Golan, R., Jacob, C., & Denzinger, J. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727205 · Cited by 133
“The first computational models based on these local connectivities between neurons are found in Fukushima’s Neocognitron [13].”
BackgroundCheng, T.-Y., Conselice, C. J., Aragón-Salamanca, A., Li, N., Bluck, A. F. L., Hartley, W. G., Annis, J., Brooks, D., Doel, P., García-Bellido, J., et al. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staa501 · Cited by 119
“The breakthrough of visual pattern recognition in machine learning started from Fukushima (1980) which proposed a hierarchical and multilayered neural network - Neocognitron.”
BackgroundMemristor crossbar deep network implementation based on a Convolutional neural network
Yakopcic, C., Alom, M. Z., & Taha, T. M. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727302 · Cited by 134
“The CNN network structure was first proposed by Fukushima in 1980 [29].”
BackgroundSeeliger, K., Fritsche, M., Güçlü, U., Schoenmakers, S., Schoffelen, J.-M., Bosch, S. E., & van Gerven, M. A. J. (2018) · NeuroImage · doi:10.1016/j.neuroimage.2017.07.018 · Cited by 121
“CNN-like architectures have been motivated from a neuroscienti fi c point of view with the introduction of the Neocognitron by Fukushima (1980).”
Application of Deep Learning on Millimeter-Wave Radar Signals: A Review
Abdu, F. J., Zhang, Y., Fu, M., Li, Y., & Deng, Z. (2021) · Sensors · doi:10.3390/s21061951 · Cited by 151
“Fukushima [85], using the concept of a hierarchical representation of receptive fields from the visual cortex, as presented by Hubel and Wiesel.”
MethodPlant disease detection model for edge computing devices
Khan, A. T., Jensen, S. M., Khan, A. R., & Li, S. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1308528 · Cited by 153
“Already in 1980, Fukushima (1980) presented a visual cortex-inspired multilayer arti fi cial neural network for image classi fi cation.”
BackgroundBurnod, Y., Grandguillaume, P., Otto, I., Ferraina, S., Johnson, P., & Caminiti, R. (1992) · The Journal of Neuroscience · doi:10.1523/jneurosci.12-04-01435.1992 · Cited by 133
Lets keep it simple, Using simple architectures to outperform deeper and more complex architecturesPreprint
Hasanpour, S. H., Rouhani, M., Fayyaz, M., & Sabokrou, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.06037 · Cited by 157
“Designing more effective networks were desirable and attempted from the advent of neural networks [24-26].”
BackgroundPredicting Semantic Descriptions from Medical Images with Convolutional Neural Networks
Schlegl, T., Waldstein, S. M., Vogl, W., Schmidt-Erfurth, U. M., & Langs, G. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19992-4_34 · Cited by 131
“They were introduced in 1980 by Fukushima [8], and have been used to solve various classification problems (cf. [9,10,11]).”
MethodPath integral guided policy search
Chebotar, Y., Kalakrishnan, M., Yahya, A., Li, A., Schaal, S., & Levine, S. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989384 · Cited by 117
“The features are learned automatically on a pose detection proxy task, using an improved version of the spatial feature points architecture [6] based on convolutional neural networks (CNNs) [29, 30].”
MethodBreast cancer outcome prediction with tumour tissue images and machine learning
Turkki, R., Bychkov, D., Lundin, M., Isola, J. J., Nordling, S., Kovanen, P. E., Verrill, C. L., von Smitten, K., Joensuu, H., Lundin, J. E., et al. (2019) · Breast Cancer Research and Treatment · doi:10.1007/s10549-019-05281-1 · Cited by 141
“CNNs are composed of consecutive, interconnected and hierarchical stages—an architecture inspired by the structure of biological neural networks [20]—making it a powerful tool to capture abstract patterns in visual data.”
BackgroundIntegrated Segmentation and Recognition of Hand-Printed Numerals
Keeler, J. D., Rumelhart, D. E., & Leow, W. K. (1990) · neural information processing systems · Cited by 131
Kinetic Energy of Hydrocarbons as a Function of Electron Density and Convolutional Neural Networks
Yao, K., & Parkhill, J. (2016) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5b01011 · Cited by 130
Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection ∗
Cabrera-Vives, G., Reyes, I., Förster, F., Estévez, P. A., & Maureira, J. C. (2017) · The Astrophysical Journal · doi:10.3847/1538-4357/836/1/97 · Cited by 136
“Convolutional neural networks (CNNs, Fukushima 1980) are a type of artificial neural network (ANN, McCulloch & Pitts 1943) that have recently gained interest in the machine learning community.”
BackgroundArtificial intelligence-powered microfluidics for nanomedicine and materials synthesis
Liu, L., Bi, M., Wang, Y., Liu, J., Jiang, X., Xu, Z., & Zhang, X. (2021) · Nanoscale · doi:10.1039/d1nr06195j · Cited by 134
Güçlü, U., & van Gerven, M. A. J. (2015) · NeuroImage · doi:10.1016/j.neuroimage.2015.12.036 · Cited by 148
“1, consists of a deep convolutional neural network (Fukushima, 1980) that nonlinearly maps stimuli to their constituent features, as well as a response model that linearly maps features to observed blood–oxygenlevel-dependent (BOLD) responses.”
BackgroundA fused deep learning architecture for viewpoint classification of echocardiography
Gao, X. W., Li, W., Loomes, M. J., & Wang, L. (2016) · Information Fusion · doi:10.1016/j.inffus.2016.11.007 · Cited by 144
“1.3 Deep learning -- Convolutional Neural Network (CNN) Deep learning neural networks refer to a class of computing machines that can learn a hierarchy of features by establishing high-level features from low-level ones and is pioneered by Fukushima [24].”
BackgroundInfluentialCNN-based image recognition for topology optimization
Lee, S., Kim, H., Lieu, Q. X., & Lee, J. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.105887 · Cited by 130
Neural networks and quantum field theory
Halverson, J., Maiti, A., & Stoner, K. (2021) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abeca3 · Cited by 156
“any architecture that is a composition of multilayer perceptrons, recurrent neural networks, skip connections [10, 11], convolutions [12, 13, 14, 15, 16] or graph convolutions [17, 18, 19, 20, 21, 22], pooling [15, 16], batch [23] or layer [24] normalization, and / or attention [25, 26].”
BackgroundIn-Depth Review of YOLOv1 to YOLOv10 Variants for Enhanced Photovoltaic Defect Detection
Hussain, M., & Khanam, R. (2024) · Solar · doi:10.3390/solar4030016 · Cited by 166
“In 1980, Fukushima presented the Neocognitron model [72], the first ANN explicitly inspired by the biological observations of Hubel and Wiesel on simple and complex cells in the visual cortex.”
Invariant Visual Responses From Attentional Gain Fields
Salinas, E., & Abbott, L. F. (1997) · Journal of Neurophysiology · doi:10.1152/jn.1997.77.6.3267 · Cited by 129
Training CNNs with Low-Rank Filters for Efficient Image ClassificationPreprint
Ioannou, Y., Robertson, D., Shotton, J., Cipolla, R., & Criminisi, A. (2015) · arXiv (Cornell University) · doi:10.13140/rg.2.1.3727.8163 · Cited by 136
Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition
Kheradpisheh, S. R., Ganjtabesh, M., & Masquelier, T. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.04.029 · Cited by 141
“For instance, using hierarchical feedforward networks with restricted receptive fields, like in the brain, has been proven useful [12, 13, 14, 15, 16, 17].”
BackgroundHamamoto, R., Komatsu, M., Takasawa, K., Asada, K., & Kaneko, S. (2019) · Biomolecules · doi:10.3390/biom10010062 · Cited by 120
“In the 1980s, Kunihiko Fukushima proposed the neocognitron, which is a hierarchical, multilayered artificial neural network [88].”
BackgroundToward understanding FinTech and its industry
Knewtson, H. S., & Rosenbaum, Z. (2020) · Managerial Finance · doi:10.1108/mf-01-2020-0024 · Cited by 127
A Theoretical Perspective on Hyperdimensional Computing
Thomas, A. H., Dasgupta, S., & Rosing, T. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12664 · Cited by 175
“…simple and general-purpose learning algorithm for linear classifiers, to neural networks [Rumelhart et al., 1986], to convolutional architectures inspired by visual cortex [Fukushima, 1980], to sparse coding [Olshausen and Field, 1996] and independent component analysis [Bell and Sejnowski, 1995].”
BackgroundMethodDalvi, C., Rathod, M., Patil, S., Gite, S., & Kotecha, K. V. (2021) · IEEE Access · doi:10.1109/access.2021.3131733 · Cited by 150
“For example, this CNN has been used in a study [126], showed that if neurons with similar parameters are applied on patches of the previous layer at various areas, a type of translational invariance is gained, is one of the primary computational models based on these nearby networks among neurons…”
MethodRoy, S., Das, N., Kundu, M., & Nasipuri, M. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.03.004 · Cited by 133
“Inspired by Hubel and Wiesel’s early work on the cat’s visual cortex [36, 37], the convolutional neural network improved on the Neocognitron model [24, 25].”
MethodDGCC: data-driven granular cognitive computing
Wang, G. (2017) · Granular Computing · doi:10.1007/s41066-017-0048-3 · Cited by 151
“Deep Learning architecture built from artificial neural networks (ANN) could date back to the Neocognitron in 1980 (Fukushima 1980).”
BackgroundWang, J. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.09.012 · Cited by 126
Fazari, A., Pellicer-Valero, Ó. J., Gómez‐Sanchís, J., Bernardi, B., Cubero, S., Benalia, S., Zimbalatti, G., & Blasco, J. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106252 · Cited by 133
Serre, T., & Riesenhuber, M. (2004) · Defense Technical Information Center (DTIC) · doi:10.21236/ada459692 · Cited by 139
“Extending previous models of object recognition in cortex [1, 2], Riesenhuber & Poggio have shown that invariant object representations (similar to the ones found in inferotemporal (IT) cortex) could be explained by the combined action of two operations:”
BackgroundBehaviour Suite for Reinforcement Learning
Osband, I., Doron, Y., Hessel, M., Aslanides, J., Sezener, E., Saraiva, A., McKinney, K., Lattimore, T., Szepesvári, C., Singh, S. P., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.03568 · Cited by 31
Exploiting fully convolutional neural networks for fast road detection
Mendes, C. C. T., Fremont, V., & Wolf, D. F. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487486 · Cited by 118
“Although its initial theory dates back to 1980 [8] its practical success started in 1998 with LeCun’s improved design [9] and consolidated in 2012 with the results obtained in the ImageNet competition [10].”
BackgroundSpindle thermal error prediction approach based on thermal infrared images: A deep learning method
Wu, C., Xiang, S., & Wansheng, X. (2021) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2021.01.013 · Cited by 125
Li, B., Wu, G., He, Y., Fan, M., & Pedrycz, W. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.105677 · Cited by 146
Ahmad, M., Distefano, S., Khan, A., Mazzara, M., Li, C., Li, H., Aryal, J., Ding, Y., Vivone, G., & Hong, D. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130428 · Cited by 153
“The CNN architecture, inspired by Hubel and Wiesel’s biological visual system [123] and Fukushima’s Neocog-nitron model [124], comprises two main stages: Feature Extraction (FE) and classification.”
Deep learning and face recognition: the state of the art
Balaban, S. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2181526 · Cited by 152
“18 They were improved and successfully applied to handwritten digit recognition by Yann LeCun in the late 90s; early applications to face recognition appeared around the same time.”
Jin, Y., Qin, C., Huang, Y., Zhao, W., & Liu, C. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105460 · Cited by 125
Detecting Harmful Content on Online Platforms: What Platforms Need vs. Where Research Efforts Go
Arora, A., Nakov, P., Hardalov, M., Sarwar, S. M., Nayak, V., Dinkov, Y., Zlatkova, D., Dent, K., Bhatawdekar, A., Bouchard, G., et al. (2023) · ACM Computing Surveys · doi:10.1145/3603399 · Cited by 167
Advances in intelligent and autonomous navigation systems for small UAS
Bijjahalli, S., Sabatini, R., & Gardi, A. (2020) · Progress in Aerospace Sciences · doi:10.1016/j.paerosci.2020.100617 · Cited by 123
Grossberg, S. (1984) · Annals of the New York Academy of Sciences · doi:10.1111/j.1749-6632.1984.tb23523.x · Cited by 132
Deep Generative Models for Synthetic Data: A Survey
Eigenschink, P., Reutterer, T., Vamosi, S., Vamosi, R., Sun, C., & Kalcher, K. (2023) · IEEE Access · doi:10.1109/access.2023.3275134 · Cited by 102
How are complex cell properties adapted to the statistics of natural stimuli?
Körding, K. P., Kayser, C., Einhäuser, W., & König, P. (2004) · Journal of Neurophysiology · doi:10.1152/jn.00149.2003 · Cited by 121
“Fukushima K. Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position.”
MethodZhong, Y., Fei, F., & Zhang, L. (2016) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.10.025006 · Cited by 120
“34,43,44 The prototype of the CNN was the LeNet models featuring receptive fields and weight sharing [see Fig.”
MethodReview on the Applications of Deep Learning in the Analysis of Gastrointestinal Endoscopy Images
Du, W., Rao, N., Liu, D., Jiang, H., Luo, C., Li, Z., Gan, T., & Zeng, B. (2019) · IEEE Access · doi:10.1109/access.2019.2944676 · Cited by 129
“CNNs first appeared in1980 [15], and Lo et al.”
BackgroundConvolutional Neural Network for the Semantic Segmentation of Remote Sensing Images
Alam, M., Wang, J., Cong, G., Yunrong, L., & Chen, Y. (2021) · Mobile Networks and Applications · doi:10.1007/s11036-020-01703-3 · Cited by 128
Adaptive machine learning for protein engineering
Hie, B. L., & Yang, K. K. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2021.11.002 · Cited by 111
Machine Learning for Auto-Segmentation in Radiotherapy Planning
Harrison, K., Pullen, H., Welsh, C., Oktay, O., Alvarez-Valle, J., & Jena, R. (2022) · Clinical Oncology · doi:10.1016/j.clon.2021.12.003 · Cited by 135
Haruna, Y., Qin, S., Chukkol, A. H. A., Yusuf, A. A., Bello, I., & Lawan, A. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110057 · Cited by 139
“Inspired by the human visual cortex by Fukushima, (1980), they consist of several layers designed to detect specific patterns in the visual field, such as edges, textures, and colors.”
Domain Adaptation by Mixture of Alignments of Second-or Higher-Order Scatter Tensors
Koniusz, P., Tas, Y., & Porikli, F. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.755 · Cited by 129
Márquez, E. Q. M., Hare, J. S., & Niranjan, M. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2805098 · Cited by 149
“Many of the core ideas behind CNNs occurred in the late 1970s with the neocognitron model [8], but failed to fully catch on for computational reasons.”
BackgroundLiao, Y., Ragai, I., Huang, Z., & Kerner, S. (2021) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2021.05.046 · Cited by 127
Conventional to Deep Ensemble Methods for Hyperspectral Image Classification: A Comprehensive Survey
Ullah, F., Ullah, I., Khan, R. U., Khan, S., Khan, K., & Pau, G. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3353551 · Cited by 131
“Adopting Hubel and Wiesel’s [169] natural visual recognition process, Neocognitron [170] isrecognizedastheoriginalhierarchicalposition-invariant pattern recognition model [171] and can be regarded as the prior of CNN [172].”
MethodSchmidhuber, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.09249 · Cited by 138
Toward an integration of deep learning and neuroscience
Marblestone, A. H., Wayne, G., & Kording, K. P. (2016) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2016.00094 · Cited by 119
“The explosion of neural network research in the 1980s ( Rumelhart et al., 1986) saw the advent of multilayer networks, followed by networks with layer-wise specializations as in convolutional networks (Fukushima, 1980; LeCun and Bengio, 1995).”
BackgroundDeep convolutional neural networks as generic feature extractors
Hertel, L., Barth, E., Kaster, T., & Martinetz, T. (2015) · 2015 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2015.7280683 · Cited by 113
Anisotropic Diffusion Descriptors
Boscaini, D., Masci, J., Rodolà, E., Bronstein, M. M., & Cremers, D. (2016) · Computer Graphics Forum · doi:10.1111/cgf.12844 · Cited by 122
“The remarkable success of deep learning architectures such as convolutional neural networks (CNN) [Fuk80,L ∗ 89] in computer vision, has driven recent attempts to bring these methods to non-Euclidean domains.”
BackgroundSelf-Trained Target Detection of Radar and Sonar Images Using Automatic Deep Learning
Zhang, P., Tang, J., Zhong, H., Ning, M., Liu, D., & Wu, K. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3096011 · Cited by 147
“R-CNNs consist of at least a backbone and a head, where the backbone utilizes convolutional neural networks (CNNs) [8]–[10] to extract features, and the head uses the features to predict both categories and locations of objects.”
A multiscale dynamic routing circuit for forming size- and position-invariant object representations
Olshausen, B. A., Anderson, C. H., & Essen, D. C. V. (1995) · Journal of Computational Neuroscience · doi:10.1007/bf00962707 · Cited by 124
Mass assembly and morphological transformations since z∼ 3 from CANDELS
Huertas-Company, M., Bernardi, M., Pérez-González, P. G., Ashby, M. L. N., Barro, G., Conselice, C., Daddi, E., Dekel, A., Dimauro, P., Faber, S. M., et al. (2016) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stw1866 · Cited by 107
Orthogonal Deep Neural Networks
Li, S., Jia, K., Wen, Y., Liu, T., & Tao, D. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2948352 · Cited by 180
Panda, P., & Roy, K. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727212 · Cited by 129
“This is done to avoid local minima and to increase the network performance [17-19].”
BackgroundConvolutional Neural Network Layers and Architectures
Bezdan, T., & Džakula, N. B. (2019) · International Scientific Conference Sinteza · doi:10.15308/sinteza-2019-445-451 · Cited by 138
Deep Architectures for Image Compression: A Critical Review
Mishra, D., Singh, S. K., & Singh, R. K. (2021) · Signal Processing · doi:10.1016/j.sigpro.2021.108346 · Cited by 130
Computational and Experimental Approaches to Visual Aesthetics
Brachmann, A., & Redies, C. (2017) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2017.00102 · Cited by 137
“Although the basic idea of CNNs has already been proposed more than three decades ago (Fukushima, 1980; Lecun and Bengio, 1995), only recently, progress in computing technologies and the availability of huge datasets for training have helped to restore the interest in using CNNs for image processing (Krizhevsky et al.”
BackgroundEnvironmental sound classification with dilated convolutions
Chen, Y., Guo, Q. J., Liang, X., Wang, J., & Qian, Y. (2018) · Applied Acoustics · doi:10.1016/j.apacoust.2018.12.019 · Cited by 116
“Being one of the most renown, CNN emerged in 1980s [15], developed in 90s [16] and served various object classification or pattern recognition tasks [17–19] for almost three decades.”
BackgroundPandey, S. K., & Janghel, R. R. (2019) · Neural Processing Letters · doi:10.1007/s11063-018-09976-2 · Cited by 131
“Motivated by this search in 1980 Fukushima, Kunihiko [51] introduced the neocognitron which was regarded as the predecessor of CNN.”
MethodRetractedA tutorial on deep learning-based data analytics in manufacturing through a welding case study
Wang, Q., Jiao, W., Wang, P. E., & Zhang, Y. (2020) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2020.04.044 · Cited by 125
The Peri-Saccadic Perception of Objects and Space
Hamker, F. H., Zirnsak, M., Calow, D., & Lappe, M. (2008) · PLoS Computational Biology · doi:10.1371/journal.pcbi.0040031 · Cited by 112
“Each single visual map consists of an input stage with ‘‘simple’’ cells for feature detection, a spatial pooling stage with ‘‘complex’’ cells to obtain increasing spatial invariance [26,27], and an intermediate gain stage at which the oculomotor feedback signal acts.”
Deep learning with support vector data description
Kim, S., Choi, Y.-H., & Lee, M. (2015) · Neurocomputing · doi:10.1016/j.neucom.2014.09.086 · Cited by 122
Evolving deep unsupervised convolutional networks for vision-based reinforcement learning
Koutník, J., Schmidhuber, J., & Gomez, F. J. (2014) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/2576768.2598358 · Cited by 131
“Convolution Neural Networks [6, 16] are deep hierarchical networks that have recently become the state of the art in pattern recognition and image processing due to the advent of fast implementations on graphics card multiprocessors (GPU) [1].”
Background
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.