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 901–1,000 of 1,028
The recognition of partially visible natural objects in the presence and absence of their occluders
Johnson, J. S., & Olshausen, B. A. (2005) · Vision Research · doi:10.1016/j.visres.2005.06.007 · Cited by 70
“…to account for amodal completion effects, instead focusing their efforts on the goodness-of-match of a feedforward analysis of the image with an object model (Fukushima, 1980; Mel, 1997; Riesenhuber & Poggio, 1999; Ullman & Bart, 2004; Ullman, Vidal-Naquet , & Sali, 2002; VanRullen & Thorpe, 2002).”
Discrete Event, Continuous Time RNNsPreprint
Mozer, M. C., Kazakov, D. V., & Lindsey, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.04110 · Cited by 79
“To explain what we mean by ‘specialized,’ consider the deep learning architecture universally used for vision—the convolutional network (Fukushima, 1980; Lecun et al., 1998; Mozer, 1987).”
BackgroundGlobal Convergence of Block Coordinate Descent in Deep LearningPreprint
Zeng, J., Lau, T. T.-K., Lin, S. B., & Yao, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.00225 · Cited by 69
“The network architectures considered in this paper exhibit generality to various types of DNNs, including but not limited to the fully (or sparse) connected MLPs (Rosenblatt, 1961), convolutional neural networks (CNNs; Fukushima, 1980; LeCun et al., 1998) and residual neural networks (ResNets; He et al.”
BackgroundCoffee Leaf Disease Recognition Based on Deep Learning and Texture Attributes
Sorte, L. X. B., Ferraz, C. T., Fambrini, F., Goulart, R. D. R., & Saito, J. H. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.09.168 · Cited by 68
Automatic Detection of COVID-19 from Chest X-ray Images with Convolutional Neural Networks
Haque, K. F., Haque, F. F., Gandy, L. M., & Abdelgawad, A. (2020) · International Conference on Computing, Electronics & Communications Engineering (iCCECE) · doi:10.1109/iccece49321.2020.9231235 · Cited by 68
Applications of deep learning in detection of glaucoma: A systematic review
Mirzania, D., Thompson, A. C., & Muir, K. W. (2020) · European Journal of Ophthalmology · doi:10.1177/1120672120977346 · Cited by 79
“24 CNNs are particularly well-suited for image analysis because they utilize both receptive fields and a parameter sharing scheme, which refers to the neurons’ ability to share their filter parameters with adjacent neurons to improve transformation of the input across the entire layer.”
BackgroundSensor array optimization for the electronic nose via different deep learning methods
Zhang, X., Wang, T., Ni, W., Zhang, Y., Lv, W., Zeng, M., Yang, J. J., Hu, N., Zhan, R., Li, G., et al. (2024) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2024.135579 · Cited by 68
Advancements in Induction Motor Fault Diagnosis and Condition Monitoring: A Comprehensive Review
Hamani, K., Kuchař, M., Kubatko, M., & Kirschner, Š. (2025) · Sensors · doi:10.3390/s25195942 · Cited by 84
“The foundational concept can be traced back to the work of Fukushima [135], who proposed an early hierarchical model capable of recognition of shift-invariant patterns.”
An integrated neural network/expert system approach for fault diagnosis
Becraft, W. R., & Lee, P. L. (1993) · Computers & Chemical Engineering · doi:10.1016/0098-1354(93)80081-w · Cited by 68
Baskin, I. I., Palyulin, V. A., & Zefirov, N. S. (1997) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci940128y · Cited by 69
P-wave first-motion polarity determination of waveform data in western Japan using deep learning
Hara, S., Fukahata, Y., & Iio, Y. (2019) · Earth Planets and Space · doi:10.1186/s40623-019-1111-x · Cited by 70
“In this study, we use the convolutional neural network (CNN) model introduced by Fukushima (1980) and LeCun et al.”
MethodFan, D., Sharad, M., Sengupta, A., & Roy, K. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2462731 · Cited by 71
“The earliest efforts involved different mathematical models for artificial neural networks, with varying neuron transfer functions and connection topologies [2], [46], [47].”
BackgroundDeformable Part Models are Convolutional Neural Networks
Girshick, R., Iandola, F., Darrell, T. J., & Malik, J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.5403 · Cited by 48
“Convolutional neural networks (CNNs) [12, 23, 27] are another influential class of models for visual recognition.”
BackgroundIoT security with Deep Learning-based Intrusion Detection Systems: A systematic literature review
Idrissi, I., Azizi, M., & Moussaoui, O. (2020) · International Conference on Intelligent Computing in Data Sciences (ICDS) · doi:10.1109/icds50568.2020.9268713 · Cited by 75
“[41], on the basis of Fukushima‘s work in 1980 [42].”
BackgroundDetection of Covid-19 in Chest X-ray Image using CLAHE and Convolutional Neural Network
Umri, B. K., Akhyari, M. W., & Kusrini, K. (2020) · International Conference on Cybernetics and Intelligent System (ICORIS) · doi:10.1109/icoris50180.2020.9320806 · Cited by 67
“CNN was established under the name of NeoCognitron proposed by Kunihiko Fukushima, a researcher from the NHK Broadcasting Science Research Laboratories, Kinuta, Setagaya, Tokyo, Japan [15].”
MethodConvolutional Neural Networks-An Extensive arena of Deep Learning. A Comprehensive Study
Singh, N., & Sabrol, H. (2021) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-021-09551-4 · Cited by 74
Long-term missing value imputation for time series data using deep neural networks
Park, J., Müller, J., Arora, B., Faybishenko, B. A., Junior, G. Z. P., Varadharajan, C., Sahu, R. K., & Agarwal, D. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-08165-6 · Cited by 103
Unsupervised Pre-training Across Image Domains Improves Lung Tissue Classification
Schlegl, T., Ofner, J., & Langs, G. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13972-2_8 · Cited by 77
“In contrast, shallow convolutional neural networks (CNN ) [1] tend to learn low-level features, which”
BackgroundTowards functional connectomics
Seung, H. S. (2011) · Nature · doi:10.1038/471170a · Cited by 67
Zoom out CNNs features for optical remote sensing change detection
Amin, A. M. E., Liu, Q., & Wang, Y. (2017) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc.2017.7984667 · Cited by 67
Alexandre, L. A. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_64 · Cited by 66
“These were originally proposed by Fukushima [10] and latter also developed by LeCun [7].”
MethodConvolutional neural network based solar photovoltaic panel detection in satellite photos
Golovko, V. A., Bezobrazov, S., Kroshchanka, A., Sachenko, A., Komar, M., & Karachka, A. (2017) · IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) · doi:10.1109/idaacs.2017.8094501 · Cited by 66
“[4] K. Fukushima, “Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position,” Biological Cybernetics, vol. 36, issue 4, pp. 193-202, 1980.”
BackgroundInfluentialNeural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements
Cordeiro, J. R., Raimundo, A., Postolache, O. A., & Sebastião, P. J. A. (2021) · Sensors · doi:10.3390/s21237990 · Cited by 76
Saqib, N., Haque, K. F., Yanambaka, V. P., & Abdelgawad, A. (2022) · Algorithms · doi:10.3390/a15040129 · Cited by 66
Neurosymbolic Reinforcement Learning and Planning: A Survey
Acharya, K., Raza, W., Dourado, C. M. J. D. M., Velasquez, A., & Song, H. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3311428 · Cited by 91
“Fukushima [31] developed the Neocog-nitron neural network, which utilized a hierarchical multilayer architecture to enable computers to learn visual patterns.”
MethodTrentin, C., Ampatzidis, Y. G., Lacerda, C., & Shiratsuchi, L. S. (2024) · Smart Agricultural Technology · doi:10.1016/j.atech.2024.100556 · Cited by 89
Ontological supervision for fine grained classification of Street View storefronts
Movshovitz-Attias, Y., Yu, Q., Stumpe, M. C., Shet, V., Arnoud, S., & Yatziv, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298778 · Cited by 65
“Convolutional Networks.”
BackgroundInfluentialA Probabilistic Framework for 3D Visual Object Representation
Detry, R., Pugeault, N., & Piater, J. H. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.64 · Cited by 67
“Higher level features recursively encode probabilistic spatial configurations of more elementary features.”
BackgroundDeep eye fixation map learning for calibration-free eye gaze tracking
Wang, K., Wang, S., & Ji, Q. (2016) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/2857491.2857515 · Cited by 73
Lähivaara, T., Kärkkäinen, L., Huttunen, J. M. J., & Hesthaven, J. S. (2018) · The Journal of the Acoustical Society of America · doi:10.1121/1.5024341 · Cited by 66
“Convolutional neural networks (CNN) were introduced [30, 18] to overcome this problem.”
BackgroundTestolin, A., Zou, W. Y., & McClelland, J. L. (2020) · Developmental Science · doi:10.1111/desc.12940 · Cited by 77
“…out of the proposal that perceptual processing takes place in a hierarchical processing sys-tem, with neurons in the lower layers encoding simple visual properties that are successively combined into more complex features (Fukushima, 1980; McClelland & Rumelhart, 1981; Riesenhuber & Poggio, 1999).”
BackgroundImproving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates
Turečková, A., Tureček, T., Oplatková, Z. K., & Rodríguez-Sánchez, A. J. (2020) · Frontiers in Robotics and AI · doi:10.3389/frobt.2020.00106 · Cited by 66
“CNN takes inspiration in biological processes in that the connectivity pattern between neurons corresponds to the organization of the animal visual cortex (Hubel and Wiesel, 1968; Fukushima, 1980; Rodríguez-Sánchez et al., 2015).”
BackgroundTranslation, rotation, and scale-invariant object recognition
Torres-Méndez, L. A., Ruiz‐Suárez, J. C., Sucar, L. E., & Gomez, G. (2000) · IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews) · doi:10.1109/5326.827484 · Cited by 66
Machine learning action parameters in lattice quantum chromodynamics
Shanahan, P. E., Trewartha, D., & Detmold, W. (2018) · Physical Review D · doi:10.1103/physrevd.97.094506 · Cited by 65
Wang, J., Luo, C., Huang, H., Zhao, H., & Wang, S. (2017) · Remote Sensing · doi:10.3390/rs9030225 · Cited by 67
“Inspired by this, Fukushima [31] first proposed the convolutional neural networks in 1980, which was then refined by LeCun in 1989 [32].”
MethodAccelerated MRI-predicted brain ageing and its associations with cardiometabolic and brain disorders
Kolbeinsson, A., Filippi, S., Panagakis, Y., Matthews, P. M., Elliott, P., Dehghan, A., & Tzoulaki, I. (2020) · Scientific Reports · doi:10.1038/s41598-020-76518-z · Cited by 72
A Review on Progress in Semantic Image Segmentation and Its Application to Medical Images
Kar, M. K., Nath, M. K., & Neog, D. R. (2021) · SN Computer Science · doi:10.1007/s42979-021-00784-5 · Cited by 71
“It was first introduced by Kunihiko Fukushima [56].”
BackgroundNawaz, M., Nazir, T., Baili, J., Khan, M. A., Kim, Y. J., & Cha, J. (2023) · Diagnostics · doi:10.3390/diagnostics13020248 · Cited by 73
“The work discussed in [58] utilized a CNN approach to classify eight types of chest abnormalities with an IOU score of 0.569, and the works in [59] and [60] also utilized DL frameworks, with IOU scores of 0.746, and 0.728, respectively.”
MethodInfluentialRecent Methods for Evaluating Crop Water Stress Using AI Techniques: A Review
Cho, S. B., Soleh, H. M., Choi, J. W., Hwang, W.-H., Lee, H., Cho, Y.-S., Cho, B., Kim, M. S., Baek, I., & Kim, G. (2024) · Sensors · doi:10.3390/s24196313 · Cited by 74
“…components of this ensemble are predictors with a tree structure and each tree is The essential components of this ensemble are predictors with a tree structure, and each tree is generated by introducing randomness into the process, which is why this procedure is referred to as a “Random…”
MethodAttention in hierarchical models of object recognition
Walther, D. B., & Koch, C. (2007) · Progress in brain research · doi:10.1016/s0079-6123(06)65005-x · Cited by 70
“In some models of object recognition, several layers of increasingly complex features follow before objects are recognized or categorized (e.g., Fukushima, 1980; LeCun et al., 1998; Serre et al., 2007b).”
BackgroundThe earliest EEG signatures of object recognition in a cued-target task are postsensory
Johnson, J. S., & Olshausen, B. A. (2005) · Journal of Vision · doi:10.1167/5.4.2 · Cited by 68
Training multi-layered neural network neocognitron
Fukushima, K. (2013) · Neural Networks · doi:10.1016/j.neunet.2013.01.001 · Cited by 65
Self-citationSparsity-Regularized HMAX for Visual Recognition
Hu, X., Zhang, J., Li, J., & Zhang, B. (2014) · PLoS ONE · doi:10.1371/journal.pone.0081813 · Cited by 68
“One of the earliest representatives is the Neocognitron [4], in which feature complexity and translation invariance are alternatingly increased in different layers.”
BackgroundCONVOLUTIONAL NEURAL NETWORK BASED DEM SUPER RESOLUTION
Chen, Z., Wang, X., Xu, Z., & Hou, W. W. (2016) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsarchives-xli-b3-247-2016 · Cited by 65
Learning Category-Specific Deformable 3D Models for Object Reconstruction
Tulsiani, S., Kar, A., Carreira, J., & Malik, J. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2574713 · Cited by 77
“Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”
BackgroundA late fusion approach for harnessing multi-cnn model high-level features
Akilan, T., Wu, Q. M. J., Safaei, A., & Jiang, W. (2017) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2017.8122666 · Cited by 67
“Inspired by this fact and Fukushima’s neural network (NN), the Neocognitron [2] many neurallyinspired deep ConvNets (DCNNs) have been proposed to date, which emulate the powerful animal visual perception system.”
BackgroundPrediction of Multidrug-Resistant TB from CT Pulmonary Images Based on Deep Learning Techniques
Gao, X. W., & Yu, Q. (2017) · Molecular Pharmaceutics · doi:10.1021/acs.molpharmaceut.7b00875 · Cited by 67
“Fukushima [18] based on biologically inspired human vision systems.”
Tong, C., Yin, X., Li, J., Zhu, T., Lv, R., Sun, L., & Rodrigues, J. J. P. C. (2018) · The Computer Journal · doi:10.1093/comjnl/bxy008 · Cited by 66
A survey on online learning for visual tracking
Abbass, M. Y., Kwon, K.-C., Kim, N., Abdelwahab, S. A., El-Samie, F. E. A., & Khalaf, A. A. M. (2021) · The Visual Computer · doi:10.1007/s00371-020-01848-y · Cited by 64
“Historically, deep learning has been used since the inception of artificial neural networks (ANNs) [91].”
BackgroundCheng, T.-Y., Conselice, C. J., Aragón‐Salamanca, A., Aguena, M., Allam, S., Andrade-Oliveira, F., Annis, J. T., Bluck, A. F. L., Brooks, D., Burke, D. L., et al. (2021) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stab2142 · Cited by 76
“The concept of machine learning in computational science started from Fukushima (1975, 1980) and Fukushima 1 https://www.darkenergysurvey.org/ et al. (1983).”
BackgroundBRAINIAC: Bringing reliable accuracy into neurally-implemented approximate computing
Grigorian, B., Farahpour, N., & Reinman, G. (2015) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2015.7056067 · Cited by 64
Learning the Compositional Nature of Visual Object Categories for Recognition
Ommer, B., & Buhmann, J. M. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.22 · Cited by 64
“For a long time, research on object recognition has aimed at building hierarchical models [25].”
BackgroundHow Convolutional Neural Networks Diagnose Plant Disease
Toda, Y., & Okura, F. (2019) · Plant Phenomics · doi:10.1155/2019/9237136 · Cited by 71
Miyagi, Y., Habara, T., Hirata, R., & Hayashi, N. (2019) · Reproductive Medicine and Biology · doi:10.1002/rmb2.12266 · Cited by 66
“…age category using super‐ vised deep learning with a convolutional neural network 30,31 that tried to mimic the visual cortex of the mammal brain 21,23,32‐35 and used L2 regularization 36,37 to categorize blastocyst images as either in the live birth or the nonlive birth category and to obtain…”
MethodRen, W., Wen, G., Xu, B. S., & Zhang, Z. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2978114 · Cited by 68
“Replacing some general matrix multiplication layers with convolutional layers and pooling layers, CNNs are kinds of particular neural networks [27].”
BackgroundP–nets: Deep Polynomial Neural Networks
Chrysos, G. G., Moschoglou, S., Bouritsas, G., Panagakis, Y., Deng, J., & Zafeiriou, S. P. (2020) · 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/cvpr42600.2020.00735 · Cited by 112
Wang, M., Zhang, H., Sun, W., Li, S., Wang, F., & Yang, G. (2020) · Remote Sensing · doi:10.3390/rs12121933 · Cited by 63
“Land cover change is the result of the combined effects of natural processes and human activities and is a core issue in the study of global change [6,7].”
BackgroundDeep learning in interstitial lung disease—how long until daily practice
Trușculescu, A. A., Manolescu, D., Tudorache, E., & Oancea, C. I. (2020) · European Radiology · doi:10.1007/s00330-020-06986-4 · Cited by 68
“The first algorithm successfully used for pattern recognition was neocognitron, in 1980, which integrated neurophysiological architecture [8, 13, 14].”
MethodVision transformers in domain adaptation and domain generalization: a study of robustness
Alijani, S., Fayyad, J., & Najjaran, H. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10353-5 · Cited by 76
“The foundational concept of using convolutions in neural networks was initiated by Fukush-ima’s development of the Neocognitron [1], a model that introduced the idea of a shift-invariant architecture.”
A survey of video-based human action recognition in team sports
Yin, H., Sinnott, R., & Jayaputera, G. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10934-9 · Cited by 76
A direct fingerprint minutiae extraction approach based on convolutional neural networks
Jiang, L., Zhao, T., Bai, C., Yong, A., & Wu, M. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727251 · Cited by 70
“Convolutional neural network was firstly proposed by Kunihiko Fukushima in 1980 [16].”
Derin Öğrenme ile Kalabalık Analizi Üzerine Detaylı Bir Araştırma
Kızrak, M. A., & Bölat, B. (2018) · Bilişim Teknolojileri Dergisi · doi:10.17671/gazibtd.419205 · Cited by 93
“Kendine sunulan bilgiyi kullanmak yerine hangi bilgiyi öğreneceğine kendi başına karar verebilen derin öğrenme ağları bu yüzden klasik yöntemlere göre daha başarılı sonuçlar üretmektedir [2-6].”
Miyagi, Y., Takehara, K., & Miyake, T. M. (2019) · Molecular and Clinical Oncology · doi:10.3892/mco.2019.1932 · Cited by 73
Shi, H., Wang, H., Qin, C., Zhao, L., & Liu, C. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105219 · Cited by 70
Using Spatio-temporal Correlations to Learn Invariant Object Recognition
Wallis, G. M. (1996) · Neural Networks · doi:10.1016/s0893-6080(96)00041-x · Cited by 63
Learning From Noisy Large-Scale Datasets With Minimal SupervisionPreprint
Veit, A., Alldrin, N., Chechik, G., Krasin, I., Gupta, A., & Belongie, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.01619 · Cited by 84
“The model comprises a fully convolutional neural network [12, 18, 19] f with two classi-”
MethodDeep Neural Network for Predicting Ore Production by Truck-Haulage Systems in Open-Pit Mines
Baek, J., & Choi, Y. (2020) · Applied Sciences · doi:10.3390/app10051657 · Cited by 74
“Deep learning models are classified into several types, such as a deep neural network (DNN) [45,46], convolutional neural network (CNN) [47,48], and recurrent neural network (RNN) [49,50], depending on the input-data type and data-processing method employed.”
BackgroundA novel Domain Adaptive Residual Network for automatic Atrial Fibrillation Detection
Jin, Y., Qin, C., Liu, J., Lin, K., Shi, H., Huang, Y., & Liu, C. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106122 · Cited by 65
Using Deep Learning to Nowcast the Spatial Coverage of Convection from Himawari-8 Satellite Data
Lagerquist, R., Stewart, J. Q., Ebert‐Uphoff, I., & Bonfanti, C. (2021) · Monthly Weather Review · doi:10.1175/mwr-d-21-0096.1 · Cited by 65
“Convolutional neural networks (CNN; Fukushima 1980; Fukushima and Miyake 1982) use convolutional filters to detect spatial and temporal features in gridded data, thus overcoming the disadvantage of FCNNs. U-nets U-nets (Ronneberger et al. 2015) retain this advantage of CNNs and also excel at…”
MethodSaltürk, S., & Kahraman, N. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09690-2 · Cited by 62
“Convolutional neural networks (CNNs) have been a game-changing innovation in image processing and computer vision [44].”
A primer on encoding models in sensory neuroscience
van Gerven, M. A. J. (2016) · Journal of Mathematical Psychology · doi:10.1016/j.jmp.2016.06.009 · Cited by 73
Cintas, C., Quinto‐Sánchez, M., Acuña-Alonzo, V., Paschetta, C., de Azevedo, S., de Cerqueira, C. C. S., Ramallo, V., Gallo, C., Poletti, G., Bortolini, M. C., et al. (2016) · IET Biometrics · doi:10.1049/iet-bmt.2016.0002 · Cited by 68
Tustison, N. J., Avants, B., Lin, Z., Feng, X., Cullen, N. C., Mata, J. F., Flors, L., Gee, J. C., Altes, T. A., Mugler, J. P., et al. (2018) · Academic Radiology · doi:10.1016/j.acra.2018.08.003 · Cited by 65
An Animal Detection and Collision Avoidance System Using Deep Learning
Saxena, A., Gupta, D. K., & Singh, S. (2020) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-5341-7_81 · Cited by 62
Sandon, P. A. (1990) · Journal of Cognitive Neuroscience · doi:10.1162/jocn.1990.2.3.213 · Cited by 61
Analysis of Fruit Images With Deep Learning: A Systematic Literature Review and Future Directions
ESPINOZA, S. P., Aguilera, C., Rojas, L. A., & Campos, P. G. (2023) · IEEE Access · doi:10.1109/access.2023.3345789 · Cited by 70
“Initially inspired by the believed functioning of the visual cortex [8], which defined the operation of simple and complex cells, these networks were first proposed by Fukushima [9].”
BackgroundMemristor-Based Artificial Neural Networks for Hardware Neuromorphic Computing
Jin, B., Wang, Z., Wang, T., & Meng, J. (2025) · Research · doi:10.34133/research.0758 · Cited by 68
“Established frameworks include the convolutional neural network (CNN) [ 5 ], which originated from the “Neocognitron” model proposed by Fukushima in 1979; the recurrent neural network (RNN) [ 6 ], developed in the 1990s through the integration of Elman networks by Elman and long short-term memory…”
Artificial neural networks as cost engineering methods in a collaborative manufacturing environment
Wang, Q. (2006) · International Journal of Production Economics · doi:10.1016/j.ijpe.2006.11.006 · Cited by 61
Procedural Modeling Using Autoencoder Networks
Yümer, M. E., Asente, P., Měch, R., & Kara, L. B. (2015) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/2807442.2807448 · Cited by 67
Challenges Facing the Detection of Colonic Polyps: What Can Deep Learning Do?
Azer, S. A. (2019) · Medicina · doi:10.3390/medicina55080473 · Cited by 62
“The work of Fukushima at the Nippon Hoso Kyokai (NHK) Broadcasting Science Research Laboratories, Tokyo, Japan, led to the proposal of “neocognition”, a mechanistic self-organizing neural network model for pattern recognition [37].”
BackgroundToward the third generation of artificial intelligence
Zhu, J., Su, H., & Zhang, B. (2020) · Scientia Sinica Informationis · doi:10.1360/ssi-2020-0204 · Cited by 62
All For One And One For All: Improving Music Separation By Bridging Networks
Sawata, R., Uhlich, S., Takahashi, S., & Mitsufuji, Y. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414044 · Cited by 61
Aggelopoulos, N. C. (2015) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2015.05.001 · Cited by 73
Image-based object recognition in man, monkey and machine
Tarr, M. J., & Bülthoff, H. H. (1999) · Object Recognition in Man, Monkey, and Machine · doi:10.7551/mitpress/5089.003.0001 · Cited by 60
EkushNet: Using Convolutional Neural Network for Bangla Handwritten Recognition
Rabby, A. S. A., Haque, S., Abujar, S., & Hossain, S. A. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.10.437 · Cited by 60
Takayuki, N. (2018) · IEICE Technical Report; IEICE Tech. Rep. · Cited by 60
Hassan, M., Ali, S., Alquhayz, H., & Safdar, K. (2020) · Scientific Reports · doi:10.1038/s41598-020-69813-2 · Cited by 63
A comparative study for glioma classification using deep convolutional neural networks
Özcan, H., Emiroğlu, B. G., Sabuncuoğlu, H., Özdoğan, S., Soyer, A., & Saygı, T. (2021) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2021080 · Cited by 60
“A convolutional neural network (CNN) [26] is a feed-forward neural network used in deep learning.”
BackgroundImage classification of marine-terminating outlet glaciers in Greenland using deep learning methods
Marochov, M., Stokes, C. R., & Carbonneau, P. E. (2021) · The Cryosphere · doi:10.5194/tc-15-5041-2021 · Cited by 40
Camera eats first: exploring food aesthetics portrayed on social media using deep learning
Gambetti, A., & Han, Q. (2022) · International Journal of Contemporary Hospitality Management · doi:10.1108/ijchm-09-2021-1206 · Cited by 64
Emerging Applications of Deep Learning in Bone Tumors: Current Advances and Challenges
Zhou, X., Wang, H., Feng, C., Xu, R., He, Y., Li, L., & Tu, C. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.908873 · Cited by 74
An Overview of Methods for Deep Learning in Neural Networks
Созыкин, А. В. (2017) · Bulletin of the South Ural State University Series Computational Mathematics and Software Engineering · doi:10.14529/cmse170303 · Cited by 61
Modelling urban networks using Variational Autoencoders
Kempinska, K., & Murcio, R. (2019) · Applied Network Science · doi:10.1007/s41109-019-0234-0 · Cited by 63
“In our work, we selected Convolutional Neural Networks (CNNs) (Fukushima 1980; LeCun et al. 1990) as the encoder and decoder architectures.”
MethodNeuroMem: Analog Graphene-Based Resistive Memory for Artificial Neural Networks
Abunahla, H., Halawani, Y., Alazzam, A., & Mohammad, B. S. (2020) · Scientific Reports · doi:10.1038/s41598-020-66413-y · Cited by 63
Model metamers reveal divergent invariances between biological and artificial neural networks
Feather, J., Leclerc, G., Mądry, A., & McDermott, J. H. (2023) · Nature Neuroscience · doi:10.1038/s41593-023-01442-0 · Cited by 59
Optimization of Convolutional Neural Networks Architectures Using PSO for Sign Language Recognition
Fregoso, J., González, C. I., & Martínez, G. E. (2021) · Axioms · doi:10.3390/axioms10030139 · Cited by 63
“The basic CNN architecture is presented in Figure 1, which consists of five layers: the input, convolution, non-linearity (ReLu), pooling, and classification layer [39,40], these are described in the following subsections.”
BackgroundMethodInfluentialGhosh, A., Urry, C. M., Wang, Z., Schawinski, K., Turp, D., & Powell, M. C. (2020) · The Astrophysical Journal · doi:10.3847/1538-4357/ab8a47 · Cited by 58
“The artificial neural network that we use for this work is a Convolutional Neural Network (CNN; Fukushima 1980; LeCun et al. 1998).”
MethodAnomaly Detection for Cyber-Security Based on Convolution Neural Network : A survey
Alabadi, M., & Celik, Y. (2020) · 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA) · doi:10.1109/hora49412.2020.9152899 · Cited by 55
“The existence of this layer, along with perceptron’s, can optimize classification accuracy [2].”
BackgroundMethodInfluentialDeleSmell: Code smell detection based on deep learning and latent semantic analysis
Zhang, Y., Ge, C., Hong, S., Tian, R., Dong, C., & Liu, J. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109737 · Cited by 54
Multi-column Deep Neural Networks for Image Classification
Cireşan, D., Meier, U., & Schmidhuber, J. (2012) · arXiv · doi:10.48550/arxiv.1202.2745 · Cited by 53
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.