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 601–700 of 1,028
Giben, X., Patel, V. M., & Chellappa, R. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7350873 · Cited by 123
“The idea of enforcing translation invariance in neural networks via weight sharing goes back to Fukoshima’s Neocognitron [15].”
BackgroundGenerating feature sets for fault diagnosis using denoising stacked auto-encoder
Thirukovalluru, R., Dixit, S., Sevakula, R. K., Verma, N. K., & Salour, A. (2016) · 2016 IEEE International Conference on Prognostics and Health Management (ICPHM) · doi:10.1109/icphm.2016.7542865 · Cited by 108
“DNN were proposed in the early 80’s by Kunihiko Fukushima [49], but training such a network took large time and gave poor generalization.”
MethodParametric convolutional neural network-domain full-waveform inversion
Wu, Y., & McMechan, G. A. (2019) · Geophysics · doi:10.1190/geo2018-0224.1 · Cited by 135
Deep learning in electron microscopy
Ede, J. M. (2020) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abd614 · Cited by 143
SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Iandola, F., Shaw, A., Krishna, R., & Keutzer, K. (2020) · Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing · doi:10.18653/v1/2020.sustainlp-1.17 · Cited by 114
Artificial vision by multi-layered neural networks: Neocognitron and its advances
Fukushima, K. (2012) · Neural Networks · doi:10.1016/j.neunet.2012.09.016 · Cited by 115
“Although classifying hypercomplex cells into lower-order and higher-order is not popular among neurophysiologists recently, it is this hypothesis that suggested the original architecture of the neocognitron model when it was first proposed by Fukushima (1980).”
BackgroundInfluentialSelf-citationTuray, T., & Vladimirova, T. (2022) · IEEE Access · doi:10.1109/access.2022.3147495 · Cited by 131
“Two decades later, Fukushima [2] introduced the first CNN model, based upon [1] and referred to as Neocognitron, which was simulated and implemented on a computer.”
MethodMoutik, O., Sekkat, H., Tigani, S., Chehri, A., Saadane, R., Tchakoucht, T. A., & Paul, A. (2023) · Sensors · doi:10.3390/s23020734 · Cited by 121
“At the time, it was assumed that a better algorithm would always give better results regardless of the data In 2012, Krizhevsky et al. [20] proved this theory wrong by announcing a deep CNN model named AlexNet for the image classification task.”
BackgroundMethodResultInfluentialDeep learning predictions of galaxy merger stage and the importance of observational realism
Bottrell, C., Hani, M. H., Teimoorinia, H., Ellison, S. L., Moreno, J., Torrey, P., Hayward, C. C., Thorp, M., Simard, L., & Hernquist, L. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz2934 · Cited by 113
“CNNs are a class of deep learning model that are particularly useful for data which exhibit topological structure such as images (Fukushima 1980; LeCun et al. 1989, 1995, 1998; Krizhevsky et al. 2012; Lecun et al. 2015).”
BackgroundCheng, F., Wang, J., Qu, L., & Qiao, W. (2017) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2017.2773426 · Cited by 118
“Deep learning utilizes ANNs with shallow architectures, such as autoencoder (AE) [24], convolutional neural network (CNN) [25], and restricted Boltzmann machine [26], as building blocks, to obtain deep ANNs (i.”
MethodPetrillo, C. E., Tortora, C., Vernardos, G., Koopmans, L. V. E., Verdoes Kleijn, G., Bilicki, M., Napolitano, N. R., Chatterjee, S., Covone, G., Dvornik, A., et al. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz189 · Cited by 107
“ConvNets (Fukushima 1980; LeCun et al. 1998) represent a state-of-the-art method of pattern recognition (Russakovsky et al. 2015).”
MethodLiu, F., Li, S., Zhang, L., Zhou, C., Ye, R., Wang, Y., & Lu, J. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.605 · Cited by 113
“Humans usually solve vision problems through a har-monious combination of reinforcement learning and hierarchical sensory processing systems [4, 22].”
BackgroundIncremental grouping of image elements in vision
Roelfsema, P. R., & Houtkamp, R. (2011) · Attention, Perception, & Psychophysics · doi:10.3758/s13414-011-0200-0 · Cited by 112
“Neurons in higher area neurons are tuned to more complex feature conjunctions (Fukushima, 1980; Riesenhuber & Poggio, 1999b).”
BackgroundFinding high-redshift strong lenses in DES using convolutional neural networks
Jacobs, C., Collett, T., Glazebrook, K., McCarthy, C., Qin, A. K., Abbott, T. M. C., Abdalla, F. B., Annis, J., Avila, S., Bechtol, K., et al. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz272 · Cited by 103
“Artificial Neural Networks (ANNs) are a machine learning technique first developed in the 1950s (Rosenblatt 1957) and more heavily researched in the 1980s and 1990s (Fukushima 1980) as non-trivial networks became computationally more tractable.”
BackgroundArtificial Neural Networks in Agriculture, the core of artificial intelligence: What, When, and Why
Castillo‐Gironés, S., Munera, S., Martínez-Sober, M., Blasco, J., Cubero, S., & Gómez‐Sanchís, J. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.109938 · Cited by 131
Deep Learning in Object Recognition, Detection, and Segmentation
Wang, X. (2016) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000071 · Cited by 128
“It was introduced by Kunihiko Fukushima in 1980 [54], and improved by Yann et al.”
MethodTraffic Sign Recognition Using Kernel Extreme Learning Machines With Deep Perceptual Features
Zeng, Y., Xu, X., Shen, D., Fang, Y., & Xiao, Z. (2016) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2016.2614916 · Cited by 110
“Representative CNN models were proposed by Fukushima [12] and LeCun [13], both of which tried to imitate the perceptual mechanism of human visual cortex and could learn more discriminative features.”
MethodAlom, M. Z., Sidike, P., Hasan, M., Taha, T. M., & Asari, V. K. (2018) · Computational Intelligence and Neuroscience · doi:10.1155/2018/6747098 · Cited by 127
Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection
Liang, X., Liu, S., Wei, Y., Liu, L., Lin, L., & Yan, S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.120 · Cited by 88
Le, Q. V. (2015) · Cited by 150
Han, L., Yu, C., Xiao, K., & Zhao, X. (2019) · Sensors · doi:10.3390/s19091960 · Cited by 110
Survey on deep learning for pulmonary medical imaging
Ma, J., Song, Y., Tian, X., Hua, Y., Zhang, R., & Wu, J. (2020) · Frontiers of Medicine · doi:10.1007/s11684-019-0726-4 · Cited by 105
“It can be regarded as the first implementation network of CNN and the first application of the concept of receptive field in the field of artificial neural network [34].”
BackgroundAre we ready for a new paradigm shift? A survey on visual deep MLP
Liu, R., Li, Y., Tao, L., Liang, D., & Zheng, H.-T. (2022) · Patterns · doi:10.1016/j.patter.2022.100520 · Cited by 153
Learning and Problem Solving with Multilayer Connectionist Systems
Anderson, C. W. (1986) · University Microfilms International eBooks · Cited by 115
A Group-Theoretic Framework for Data AugmentationPreprint
Chen, S., Dobriban, E., & Lee, J. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.10905 · Cited by 259
“This is the inductive bias of CNNs, and the idea dates back at least to the neocognitron (Fukushima, 1980). To make models invariant to arbitrary transforms beyond the ones built into the architecture, data augmentation is commonly used. Roughly speaking, the model is trained not just with the original data, but also…”
InfluentialDisaster detection from aerial imagery with convolutional neural network
Amit, S. N. K. B., & Aoki, Y. (2017) · International Electronics Symposium (IES) · doi:10.1109/kcic.2017.8228593 · Cited by 109
“[15]–[17] are examples of neural inspired models.”
Özyurt, F. (2019) · The Journal of Supercomputing · doi:10.1007/s11227-019-03106-y · Cited by 115
Ikram, R. M. A., Mostafa, R. R., Chen, Z., Parmar, K. S., Kişi, Ö., & Zounemat‐Kermani, M. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11020259 · Cited by 111
RETRACTED CHAPTER: UAVs Applied to the Counting and Monitoring of Animals
Chamoso, P., Raveane, W., Parra, V., & Arrieta, A. G. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-07596-9_8 · Cited by 108
“For every window analyzed, the output values of the CNN are processed with the softmax activation function described in Equation 1, where y i is the resulting value of the network for output neuron i.”
InfluentialAN OVERVIEW OF POPULAR DEEP LEARNING METHODS
Coşkun, M., Yıldırım, Ö., Uçar, A., & Demir, Y. (2017) · European Journal of Technic · doi:10.23884/ejt.2017.7.2.11 · Cited by 126
Evolutionary design of neural network architectures: a review of three decades of research
Ünal, H. T., & Başçiftçi, F. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-021-10049-5 · Cited by 122
“In 1980, Fukushima (1980) laid the foundations of Convolutional Neural Networks (CNN), with the Neocognitron inspired by Hubel and Wiesel’s studies on neuroscience (1959, 1962).”
BackgroundMethodRobust face analysis using convolutional neural networks
Fasel, B. (2003) · Object recognition supported by user interaction for service robots · doi:10.1109/icpr.2002.1048231 · Cited by 105
Biometric Authentication Using Noisy Electrocardiograms Acquired by Mobile Sensors
Choi, H.-S., Lee, B., & Yoon, S. (2016) · IEEE Access · doi:10.1109/access.2016.2548519 · Cited by 116
“Although our approach is based on shallow learning, deep learning approaches such as convolutional neural networks (CNN) [46] or recurrent neural networks (RNN) [47] could be used to further improve performance.”
MethodGeneric feature learning for wireless capsule endoscopy analysis
Seguí, S., Drozdzal, M., Pascual, G., Radeva, P. I., Malagelada, C., Azpiroz, F., & Vitria, J. M. (2016) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2016.10.011 · Cited by 110
Dang, H., Sun, M., Zhang, G., Qi, X., Zhou, X., & Chang, Q. (2019) · IEEE Access · doi:10.1109/access.2019.2918792 · Cited by 107
Wang, Z., Shadpour, S., Chan, E., Rotondo, V., Wood, K. M., & Tulpan, D. (2021) · Journal of Animal Science · doi:10.1093/jas/skab022 · Cited by 112
“…morphometric feature extraction, and feature selection as part of complex neural network architectures such as convolutional neural networks—CNNs (Fukushima, 1980), recurrent convolutional neural networks—RCNNs/RNNs (Spoerer et al., 2017), recurrent attention models—RAMs (Mnih et al., 2014),…”
BackgroundAn improved faster-RCNN model for handwritten character recognition
Albahli, S., Nawaz, M., Javed, A., & Irtaza, A. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-05471-4 · Cited by 107
Boroumand, A., Ghose, S., Akin, B., Narayanaswami, R., Junior, G. F. D. O., Ma, X., Shiu, E., & Mutlu, O. (2021) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1109/pact52795.2021.00019 · Cited by 153
Ghodrati, M., Khaligh‐Razavi, S., & Lehky, S. R. (2017) · Progress in Neurobiology · doi:10.1016/j.pneurobio.2017.06.002 · Cited by 120
Cao, Q. D., & Choe, Y. (2020) · Natural Hazards · doi:10.1007/s11069-020-04133-2 · Cited by 112
“resent 32 ways to extract features from the previous layers and form a stack of 32 feature matrices. Another interesting property of CNN is its robustness to shifts and distortion of the input images [15]. This is crucial since in many datasets, the objects of interest are usually not positioned right at the center of…”
BackgroundNiu, Y., Mostaghimi, P., Shabaninejad, M., Świętojański, P., & Armstrong, R. T. (2020) · Water Resources Research · doi:10.1029/2019wr026597 · Cited by 107
Su, H., Wang, A., Zhang, T., Qin, T., Du, X., & Yan, X. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102440 · Cited by 120
Roelfsema, P. R., Engel, A. K., König, P., & Singer, W. (1996) · Journal of Cognitive Neuroscience · doi:10.1162/jocn.1996.8.6.603 · Cited by 108
Ellis, H. P., Greenslade, M., Powell, B., Spiteri, I., Sottoriva, A., & Kurian, K. M. (2015) · Frontiers in Oncology · doi:10.3389/fonc.2015.00251 · Cited by 111
Zhang, G., Si, Y., Wang, D., Yang, W., & Sun, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2955555 · Cited by 110
“Deep learning architectures such as deep neural networks [21], deep belief networks [22], recurrent neural networks [23] and convolutional neural networks (CNN) [24] have been applied to various fields.”
InfluentialGomez-Fernandez, M., Higley, K. A., Tokuhiro, A., Welter, K. B., Wong, W., & Yang, H. (2019) · Nuclear Engineering and Design · doi:10.1016/j.nucengdes.2019.110479 · Cited by 115
Neural Networks and Deep Learning
Brunton, S. L., & Kutz, J. N. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108380690.007 · Cited by 111
Brain activity and cognition: a connection from thermodynamics and information theory
Collell, G., & Fauquet, J. (2015) · Frontiers in Psychology · doi:10.3389/fpsyg.2015.00818 · Cited by 117
Hatipoğlu, N., & Bilgin, G. (2017) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-017-1630-1 · Cited by 114
Deep Polynomial Neural Networks
Chrysos, G. G., Moschoglou, S., Bouritsas, G., Deng, J., Panagakis, Y., & Zafeiriou, S. P. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3058891 · Cited by 153
“Despite the variety of linear transformations [1], [2], [26] and activation functions [27], [28] being used, the effort to extend this paradigm has not”
MethodDeep Learning for Computer Vision: A Brief Review
Shetty, K. R., Soorinje, V. S., Dsouza, P., & Swasthik (2022) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-2898 · Cited by 109
Basir, S., & Senocak, I. (2022) · Journal of Computational Physics · doi:10.1016/j.jcp.2022.111301 · Cited by 104
Development of residual learning in deep neural networks for computer vision: A survey
Xu, G., Wang, X., Wu, X., Leng, X., & Xu, Y. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109890 · Cited by 114
“Afterward, Fukushima proposed a neural network model, Neocognitron [8] [9], imitated from Hubel and Wiesel’s hierarchy model for the visual nervous system.”
CNNs, RNNs and Transformers in human action recognition: a survey and a hybrid model
Alomar, K., Aysel, H. I., & Cai, X. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11388-3 · Cited by 133
“This section aims to elucidate the underlying RNN techniques and the subsequent advancements that were incorporated into them, ultimately leading to the final formulation of the Transformer architecture.”
A Convolutional Subunit Model for Neuronal Responses in Macaque V1
Vintch, B., Movshon, J. A., & Simoncelli, E. P. (2015) · The Journal of Neuroscience · doi:10.1523/jneurosci.2815-13.2015 · Cited by 103
“Fukushima (1980) suggested that the spatial pooling of rectified filter responses is a canonical operation that is repeated in all visual cortical areas to impart translation-invariance.”
BackgroundHan, M., Feng, Y., Zhao, X., Sun, C., Hong, F., & Liu, C. (2019) · IEEE Access · doi:10.1109/access.2019.2955957 · Cited by 104
“Usually the fully connected layer is at the end of the convolutional neural network, which is the same as the connection for traditional neural network neurons [23].”
BackgroundDong, L.-J., Tang, Z., Li, X., Chen, Y., & Xue, J. (2020) · Journal of Central South University · doi:10.1007/s11771-020-4530-8 · Cited by 103
Automated heartbeat classification based on deep neural network with multiple input layers
Shi, H., Qin, C., Xiao, D., Zhao, L., & Liu, C. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105036 · Cited by 102
The application of artificial neural networks in metabolomics: a historical perspective
Mendez, K. M., Broadhurst, D., & Reinke, S. N. (2019) · Metabolomics · doi:10.1007/s11306-019-1608-0 · Cited by 105
“The original aim of ANNs was to understand brain and nervous system function by mathematically modelling signal transfer between neurons (Fukushima 1980; Robinson 1992).”
Automatic cardiac cine MRI segmentation and heart disease classification
Ammar, A., Bouattane, O., & Youssfi, M. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.101864 · Cited by 109
Deep Learning: Layer-Wise Learning of Feature Hierarchies
Schulz, H., & Behnke, S. (2012) · Künstliche Intell. · doi:10.1007/s13218-012-0198-z · Cited by 126
Mohammadian Rad, N., Kia, S. M., Zarbo, C., van Laarhoven, T., Jurman, G., Venuti, P., Marchiori, E., & Furlanello, C. (2018) · Signal Processing · doi:10.1016/j.sigpro.2017.10.011 · Cited by 94
GlacierNet: A Deep-Learning Approach for Debris-Covered Glacier Mapping
Xie, Z., Haritashya, U. K., Asari, V. K., Young, B. W., Bishop, M. P., & Kargel, J. S. (2020) · IEEE Access · doi:10.1109/access.2020.2991187 · Cited by 101
Zheng, Q., Yang, L., Zeng, B., Li, J., Guo, K., Liang, Y., & Liao, G. (2020) · EClinicalMedicine · doi:10.1016/j.eclinm.2020.100669 · Cited by 108
“In the 1980s, artificial neural networks (ANNs) were developed [10], resulting in a surge of machine learning (ML) based on statistical models.”
Deep learning neural network tools for proteomics
Meyer, J. G. (2021) · Cell Reports Methods · doi:10.1016/j.crmeth.2021.100003 · Cited by 101
“Roughly 15 years later, Siqi Lui’s group revisited the use of neural networks for peptide retention time prediction by using LSTM, but also CNNs (Fukushima, 1980).”
BackgroundMethodInfluentialDeep insight into daily runoff forecasting based on a CNN-LSTM model
Deng, H., Chen, W., & Huang, G. (2022) · Natural Hazards · doi:10.1007/s11069-022-05363-2 · Cited by 107
“Inspired by the visual perception of living creatures (Fukushima 1980), convolutional neural networks (CNNs) were developed by LeCun et al. (1989) and significantly out-perform fully connected neural networks (Xu and Liang 2021).”
MethodA unified systolic architecture for artificial neural networks
Kung, S., & Hwang, J. (1989) · Journal of Parallel and Distributed Computing · doi:10.1016/0743-7315(89)90065-8 · Cited by 101
S-CNN-BASED SHIP DETECTION FROM HIGH-RESOLUTION REMOTE SENSING IMAGES
Zhang, R., Yao, J., Zhang, K., Feng, C., & Zhang, J. (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/isprs-archives-xli-b7-423-2016 · Cited by 100
“The concept of CNN was inspired by ( Fukushima, 1980), who presented “neocognitron” as a hierarchical and sift-invariant model, which is an early attempt in pattern recognition.”
MethodData synthesis and adversarial networks: A review and meta-analysis in cancer imaging
Osuala, R. O., Kushibar, K., Garrucho, L., Linardos, A., Szafranowska, Z., Klein, S., Glocker, B., Díaz, O., & Lekadir, K. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102704 · Cited by 118
Salinas, E., & Abbott, L. F. (2001) · Progress in brain research · doi:10.1016/s0079-6123(01)30012-2 · Cited by 109
Spatiotemporal Dynamics Underlying Object Completion in Human Ventral Visual Cortex
Tang, H., Buia, C., Madhavan, R., Crone, N. E., Madsen, J. R., Anderson, W. S., & Kreiman, G. (2014) · Neuron · doi:10.1016/j.neuron.2014.06.017 · Cited by 95
“Whereas recognition of whole objects has been successfully modeled by purely bottom-up architectures (Deco and Rolls, 2004; Fukushima, 1980; Riesenhuber and Poggio, 1999), those models struggle to identify objects with only partial information (Johnson and Olshausen, 2005; O’Reilly et al.”
BackgroundInfluentialGao, K., Ahmad, M. O., & Swamy, M. N. S. (1994) · IEEE Transactions on Circuits and Systems II Analog and Digital Signal Processing · doi:10.1109/82.331542 · Cited by 100
DeepSat - A Learning framework for Satellite ImageryPreprint
Basu, S., Ganguly, S., Mukhopadhyay, S., DiBiano, R., Karki, M., & Nemani, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.03602 · Cited by 115
“Convolutional Neural Network (CNN) first introduced in [13] is a hierarchical model inspired by the human visual cortical system [16].”
BackgroundA comprehensive review of recent advances on deep vision systems
Abbas, Q., Ibrahim, M. E. A., & Jaffar, M. A. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-018-9633-3 · Cited by 99
“Deep learning concept has a long history since the initiation of artificial neural networks (ANNs) (Fukushima 1980).”
BackgroundRegion-Based Discriminative Feature Pooling for Scene Text Recognition
Lee, C., Bhardwaj, A., Di, W., Jagadeesh, V., & Piramuthu, R. (2014) · 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.2014.516 · Cited by 106
“Several other research areas have utilized low-level image features computed using linear and non-linear transformations of the input image [8] and then extract midlevel feature representations using sub-regions based pooling schema.”
BackgroundExtremely parallel memristor crossbar architecture for convolutional neural network implementation
Yakopcic, C., Alom, M. Z., & Taha, T. M. (2017) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7966055 · Cited by 100
Predictive coding as a model of cognition
Spratling, M. (2016) · Cognitive Processing · doi:10.1007/s10339-016-0765-6 · Cited by 104
“…several hierarchical models of invariant object recognition which employ alternating layers of neurons to form more specialised representations in one layer, and more invariant representations in the next layer (Fukushima, 1980; LeCun et al., 2010; Riesenhuber and Poggio, 1999; Serre et al., 2007).”
BackgroundMethodHandwritten Hangul recognition using deep convolutional neural networks
Kim, I., & Xie, X. S. (2014) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-014-0229-4 · Cited by 107
Convolution by Evolution: Differentiable Pattern Producing Networks
Fernando, C., Banarse, D., Reynolds, M., Besse, F., Pfau, D., Jaderberg, M., Lanctot, M., & Wierstra, D. (2016) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/2908812.2908890 · Cited by 113
“Convolutional neural networks [6, 16] have made great strides in recent years in practical performance [14], to the point where they are now a critical component of many of the best systems for challenging artificial intelligence tasks [9, 2, 18, 12].”
BackgroundFive points to check when comparing visual perception in humans and machines
Funke, C. M., Borowski, J., Stosio, K., Brendel, W., Wallis, T. S. A., & Bethge, M. (2021) · Journal of Vision · doi:10.1167/jov.21.3.16 · Cited by 70
“One famous example is the hierarchical HMAX-model (Fukushima, 1980; Riesenhuber & Poggio, 1999).”
BackgroundContour Decouples Gamma Activity Across Texture Representation in Monkey Striate Cortex
Gail, A. (2000) · Cerebral Cortex · doi:10.1093/cercor/10.9.840 · Cited by 98
Autoencoder With Invertible Functions for Dimension Reduction and Image Reconstruction
Yang, Y., Wu, Q. M. J., & Wang, Y. (2016) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2016.2637279 · Cited by 101
Polz, J., Chwala, C., Graf, M., & Kunstmann, H. G. (2020) · Atmospheric measurement techniques · doi:10.5194/amt-13-3835-2020 · Cited by 96
Option pricing using Machine Learning
Ivașcu, C.-F. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113799 · Cited by 116
Coppola, F., Faggioni, L., Gabelloni, M., De Vietro, F., Mendola, V., Cattabriga, A., Cocozza, M. A., Vara, G., Piccinino, A., Lo Monaco, S., et al. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.710982 · Cited by 94
“While the first CNN was implemented in 1980 by Fukushima (1980), CNNs were formalized as we know them now by LeCun et al. (1998).”
MethodA Two-Stage Cascade Model of BOLD Responses in Human Visual Cortex
Kay, K., Winawer, J. A., Rokem, A., Mezer, A., & Wandell, B. A. (2013) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003079 · Cited by 103
“The success of the SOC model is consistent with the long-standing hypothesis that the visual system can be characterized as a cascade of operations [29–34].”
ResultJadi, M. P., Behabadi, B. F., Poleg-Polsky, A., Schiller, J., & Mel, B. W. (2014) · Proceedings of the IEEE · doi:10.1109/jproc.2014.2312671 · Cited by 96
Non-linear Convolution Filters for CNN-Based Learning
Zoumpourlis, G., Doumanoglou, A., Vretos, N., & Daras, P. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.510 · Cited by 124
“One of the first biologically-inspired neural networks, was Fukushima’s Neocognitron [8], which was the prede-cessor of CNN, as it was introduced by LeCun et al. in [6].”
MethodBeyond the feedforward sweep: feedback computations in the visual cortex
Kreiman, G., & Serre, T. (2020) · Annals of the New York Academy of Sciences · doi:10.1111/nyas.14320 · Cited by 83
“14,17,18 Starting with Fukushima’s neocognitron, 19 computational models constrained by the anatomy and physiology of the visual cortex (VC) (see Refs.”
BackgroundMeyer, R., Weichselbaum, M., & Hauser, A. W. (2020) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.0c00580 · Cited by 96
Real-Time Human Detection Using Deep Learning on Embedded Platforms: A Review
Rahmaniar, W., & Hernawan, A. (2021) · Journal of Robotics and Control (JRC) · doi:10.18196/jrc.26123 · Cited by 107
Biophysiologically Plausible Implementations of the Maximum Operation
Yu, A. J., Giese, M. A., & Poggio, T. (2002) · Neural Computation · doi:10.1162/089976602760805313 · Cited by 103
“Mechanisms similar to those proposed by Fukushima (1980) to explain learning in the Neocognitron may be explored.”
Statistical Foundations of Actuarial Learning and its Applications
Wüthrich, M. V., & Merz, M. (2023) · Springer Actuarial · doi:10.1007/978-3-031-12409-9 · Cited by 95
Neural representation for object recognition in inferotemporal cortex
Lehky, S. R., & Tanaka, K. (2016) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2015.12.001 · Cited by 101
Noise robust sound event classification with convolutional neural network
Özer, İ., Özer, Z., & Fındık, O. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.07.021 · Cited by 95
Recursive Autoencoders-Based Unsupervised Feature Learning for Hyperspectral Image Classification
Zhang, X., Liang, Y., Li, C., Huyan, N., Jiao, L., & Zhou, H. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2737823 · Cited by 95
“For feature learning, many unsupervised feature learning methods based on deep learning have been proposed [18]–[20].”
MethodMa, M., Marturi, N., Li, Y., Leonardis, A., & Stolkin, R. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.11.026 · Cited by 98
Image Denoising using Deep Learning: Convolutional Neural Network
Ghose, S., Singh, N., & Singh, P. (2020) · International Conference on Cloud Computing, Data Science & Engineering (Confluence) · doi:10.1109/confluence47617.2020.9057895 · Cited by 104
Kandel, I., Castelli, M., & Popovič, A. (2020) · Journal of Imaging · doi:10.3390/jimaging6090092 · Cited by 106
“The convolutional neural network (CNN) has been used as an image classification algorithm for nearly two decades [2].”
MethodZheng, C., Zhang, H., Liu, W., Luo, X., Li, A., Li, X., & Moore, B. C. J. (2023) · Trends in Hearing · doi:10.1177/23312165231209913 · Cited by 135
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.