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 401–500 of 1,028
Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus
Zhang, Y., An, L., Xu, J., Zhang, B., Zheng, W. J., Hu, M., Tang, J., & Yue, F. (2018) · Nature Communications · doi:10.1038/s41467-018-03113-2 · Cited by 188
Kalfarisi, R., Wu, Z. Y., & Soh, K. (2020) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000890 · Cited by 184
Celard, P., Iglesias, E. L., Sorribes-Fdez, J. M., Romero, R., Vieira, A. S., & Borrajo, L. (2023) · Neural Computing and Applications · doi:10.1007/s00521-022-07953-4 · Cited by 188
“Although convolutions are known since late 1970s [50], it was not until 1995 that they were applied to medical images [51], and in 1998 in a real-world application in LeNet [36] for hand-written digit recognition.”
BackgroundUltrasound image-based thyroid nodule automatic segmentation using convolutional neural networks
Ma, J., Wu, F., Jiang, T., Zhao, Q., & Kong, D. (2017) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-017-1649-7 · Cited by 187
Predicting Response to Neoadjuvant Chemotherapy with PET Imaging Using Convolutional Neural Networks
Ypsilantis, P.-P., Siddique, M., Sohn, H.-M., Davies, A., Cook, G., Goh, V., & Montana, G. (2015) · PLOS ONE · doi:10.1371/journal.pone.0137036 · Cited by 185
“In very recent years, bio-logically-inspired convolutional neural networks (CNN) have shown the ability to learn hierar-chically-organised, low-to high-level features from raw images [26, 27], and yield state-of-the-art performance in the classification of both natural and medical images [28 – 31].”
BackgroundConvolutional neural networks for automated damage recognition and damage type identification
Modarres, C., Astorga, N., Droguett, E. L., & Meruane, V. (2018) · Structural Control and Health Monitoring · doi:10.1002/stc.2230 · Cited by 185
Deep neural networks in computational neuroscience
Kietzmann, T. C., McClure, P., & Kriegeskorte, N. (2019) · Oxford Research Encyclopedia of Neuroscience · doi:10.1093/acrefore/9780190264086.013.46 · Cited by 186
Object recognition and detection with deep learning for autonomous driving applications
Uçar, A., Demir, Y., & Güzeliş, C. (2017) · SIMULATION · doi:10.1177/0037549717709932 · Cited by 182
“The first ideas relating to CNNs were originally given by Fukushima with hierarchically organized image transformations to simulate the human visual system by using the concepts in Hubel and Wiesel(34) in 1980.(35) Unlike conventional CNNs, however, his work does not contain a shared weight.”
MethodDiagnosis of Lung Cancer Based on CT Scans Using CNN
Al-Yasriy, H. F., AL-Husieny, M. S., Mohsen, F. Y., Khalil, E. A., & Hassan, Z. S. (2020) · IOP Conference Series: Materials Science and Engineering · doi:10.1088/1757-899x/928/2/022035 · Cited by 159
Paul, R., Hawkins, S., Balagurunathan, Y., Schabath, M., Gillies, R., Hall, L., & Goldgof, D. (2016) · Tomography · doi:10.18383/j.tom.2016.00211 · Cited by 181
“The predecessor of convolutional networks the “neocognitron” was proposed by Fukushima (3) in 1980.”
A Lightweight Attention-Based Convolutional Neural Networks for Tomato Leaf Disease Classification
Bhujel, A., Kim, N.-E., Arulmozhi, E., Basak, J. K., & Kim, H.-T. (2022) · Agriculture · doi:10.3390/agriculture12020228 · Cited by 165
“Although CNN was introduced by Neocognitron [5] and LeNet [6] in the 1980s, the application of CNN skyrocketed after it successfully classified ImageNet 1000 datasets by AlexNet [7] using graphical processing unit (GPU).”
MethodFifty years of computer analysis in chest imaging: rule-based, machine learning, deep learning
van Ginneken, B. (2017) · Radiological Physics and Technology · doi:10.1007/s12194-017-0394-5 · Cited by 177
“Work on convnets dates back to the 1970s [12], and already in 1995, they were applied to medical image analysis by Lo et al. [13].”
MethodJEDI-net: a jet identification algorithm based on interaction networks
Moreno, E. A., Cerri, O., Duarte, J. M., Newman, H. B., Nguyen, T. Q., Periwal, A., Maurizio Pierini, B., Serikova, A., Spiropulu, M., & Vlimant, J.-R. (2020) · The European Physical Journal C · doi:10.1140/epjc/s10052-020-7608-4 · Cited by 200
Sothe, C., De Almeida, C. M., Schimalski, M. B., La Rosa, L. E. C., Castro, J. D. B., Feitosa, R. Q., Dalponte, M., Lima, C. L., Liesenberg, V., Miyoshi, G. T., et al. (2020) · GIScience & Remote Sensing · doi:10.1080/15481603.2020.1712102 · Cited by 176
“The fi rst deep learning technique called CNN was introduced by Fukushima (1980), inspired by the animal visual cortex operation, in which each neuron/kernel is focused on processing information associated with a restricted location of the visual fi eld, known as the “ receptive fi eld.”
MethodThree critical factors affecting automated image species recognition performance for camera traps
Schneider, S., Greenberg, S., Taylor, G. W., & Kremer, S. C. (2020) · Ecology and Evolution · doi:10.1002/ece3.6147 · Cited by 159
A comprehensive survey on optimizing deep learning models by metaheuristics
Akay, B., Karaboga, D., & Akay, R. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-09992-0 · Cited by 169
“CNN (Fukushima 1980) is one of the most used DNN models generally used for gridstructured data, such as images.”
BackgroundMethodFrom neural PCA to deep unsupervised learning
Valpola, H. (2015) · Advances in Independent Component Analysis and Learning Machines · doi:10.1016/b978-0-12-802806-3.00008-7 · Cited by 181
Recognizing emotions expressed by body pose: A biologically inspired neural model
Schindler, K., Van Gool, L., & de Gelder, B. (2008) · Neural Networks · doi:10.1016/j.neunet.2008.05.003 · Cited by 174
“MAX pooling as a basic operation of the visual pathway has been proposed by [26] and has been strongly advocated and investigated in detail by [51].”
MethodAlabadi, M., Habbal, A., & Wei, X. H. (2022) · IEEE Access · doi:10.1109/access.2022.3185049 · Cited by 211
“The problem of vanishing gradient [107] can be overridden by LSTM. Additionally, there is an important implementation of deep learning is the convolution neural network (CNN), where the data has high dimensions, which is challenging to handle with the classical neural network [108].”
BackgroundBayoudh, K. (2024) · Information Fusion · doi:10.1016/j.inffus.2023.102217 · Cited by 159
Medical image registration using deep neural networks: A comprehensive review
Boveiri, H. R., Khayami, R., Javidan, R., & Mehdizadeh, A. (2020) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2020.106767 · Cited by 179
Retinal Vessel Segmentation using Deep Neural Networks
Melinscak, M., Prentasic, P., & Loncaric, S. (2015) · Proceedings of the 10th International Conference on Computer Vision Theory and Applications · doi:10.5220/0005313005770582 · Cited by 175
Kong, Z., Cui, Y., Xia, Z., & Lv, H. (2019) · Applied Sciences · doi:10.3390/app9194156 · Cited by 170
“Convolutional Neural Network The convolutional neural network (CNN) was proposed by Fukushima [46] and is mainly aimed at pattern recognition and image processing.”
BackgroundNeural network model for selective attention in visual pattern recognition and associative recall
Fukushima, K. (1987) · Applied Optics · doi:10.1364/ao.26.004985 · Cited by 176
Self-citationStructured Event Memory: A neuro-symbolic model of event cognition.
Franklin, N. T., Norman, K. A., Ranganath, C., Zacks, J. M., & Gershman, S. J. (2020) · Psychological Review · doi:10.1037/rev0000177 · Cited by 177
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
Gulcehre, C., Cho, K., Pascanu, R., & Bengio, Y. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-662-44848-9_34 · Cited by 167
“Pooling operators have been widely used in convolutional neural networks (CNN) [21,10,27] to reduce the dimensionality of a high-dimensional output of a convolutional layer.”
MethodNakayama, K., & Martini, P. (2011) · Vision Research · doi:10.1016/j.visres.2010.09.003 · Cited by 169
“…recognition, some treatments suggest recoding of the image by concatenating elementary units inspired by Hubel and Wiesel era neurophysiology (Fukushima, 1980; Riesenhuber & Poggio, 1999) whereas other approaches have attempted to develop image fragment detectors that are particularly…”
An overview of deep learning methods for multimodal medical data mining
Behrad, F., & Saniee Abadeh, M. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117006 · Cited by 159
A review of deep learning applications in human genomics using next-generation sequencing data
Alharbi, W. S., & Rashid, M. (2022) · Human Genomics · doi:10.1186/s40246-022-00396-x · Cited by 159
Qin, C., Shi, G., Tao, J., Yu, H., Jin, Y., Lei, J., & Liu, C. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.107386 · Cited by 175
Deep Convolution Neural Networks in Computer Vision: a Review
Yoo, H.-J. (2015) · IEIE Transactions on Smart Processing and Computing · doi:10.5573/ieiespc.2015.4.1.035 · Cited by 173
“A hierarchical multilayered artificial neural network called neocognitron was proposed by Fukushima in 1980 [19].”
BackgroundMethodInvariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet
Rolls, E. T. (2012) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2012.00035 · Cited by 172
“In VisNet no attempt is made to train the response properties of simple cells, but instead we start with a defined series of filters to perform fixed feature extraction to a level equivalent to that of simple cells in V1, as have other researchers in the field (Fukushima, 1980; Buhmann et al., 1991; Hummel and Biederm…”
BackgroundMethodInfluentialDeep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
Kheradpisheh, S. R., Ghodrati, M., Ganjtabesh, M., & Masquelier, T. (2016) · Scientific Reports · doi:10.1038/srep32672 · Cited by 134
“Early models were only comprised of a few layers [8, 9, 10, 11, 12], while the new generation, called “deep convolutional neural networks” (DCNNs) contain many layers (8 and above).”
Meli, R., Morris, G. M., & Biggin, P. C. (2022) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2022.885983 · Cited by 155
“Convolutional neural networks (Fukushima 1980; Le Cun et al., 1989; Lecun et al., 1998; Krizhevsky et al., 2017) are a class of neural networks that tries to overcome some of the limitations of feed-forward neural networks, by using convolution operations instead of matrix multiplication in some of…”
BackgroundGenerative artificial intelligence: a historical perspective
He, R., Cao, J., & Tan, T. N. (2025) · National Science Review · doi:10.1093/nsr/nwaf050 · Cited by 209
Trade-Off between Object Selectivity and Tolerance in Monkey Inferotemporal Cortex
Zoccolan, D., Kouh, M., Poggio, T., & DiCarlo, J. J. (2007) · The Journal of Neuroscience · doi:10.1523/jneurosci.1897-07.2007 · Cited by 169
Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography
Verhelst, P.-J., Smolders, A., Beznik, T., Meewis, J., Vandemeulebroucke, A., Shaheen, E., Gerven, A. V., Willems, H., Politis, C., & Jacobs, R. (2021) · Journal of Dentistry · doi:10.1016/j.jdent.2021.103786 · Cited by 179
“These networks were already introduced in the 1980s [19,20].”
BackgroundTajbakhsh, N., & Suzuki, K. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.09.029 · Cited by 171
“A CNN can be viewed as a simplified version of the Neocog2 nitron model [23, 24, 25], which was proposed to simulate 3 the human visual system in 1980 [23].”
MethodLearning optimized features for hierarchical models of invariant object recognition.
Wersing, H., & Körner, E. (2003) · Neural Computation · doi:10.1162/089976603321891800 · Cited by 169
“receptive field centers, like in a classical weight-sharing or convolutional architecture ( Fukushima 1980; LeCun, Bottou, Bengio, & Haffner 1998).”
BackgroundInfluentialHyperfeatures – Multilevel Local Coding for Visual Recognition
Agarwal, A., & Triggs, B. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_3 · Cited by 163
“Hyperfeature stacks also have analogies with multilevel neural models such as the neocognitron [18], Convolutional Neural Networks (CNN) [28] and HMAX [38].”
MethodMachine Learning for Advanced Wireless Sensor Networks: A Review
Kim, T., Vecchietti, L. F., Choi, K., Lee, S., & Har, D. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3035846 · Cited by 161
Comprehensive Review of Vision-Based Fall Detection Systems
Gutiérrez, J., Rodríguez, V., & Martín, S. (2021) · Sensors · doi:10.3390/s21030947 · Cited by 198
“The first neural network model with visual pattern recognition capability was proposed by Fukushima [126], and, based on it, LeCun and some collaborators developed CNNs with excellent results in pattern recognition, as shown in [127,128].”
MethodMacpherson, T., Churchland, A., Sejnowski, T., DiCarlo, J., Kamitani, Y., Takahashi, H., & Hikida, T. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.09.018 · Cited by 144
“…cognition within the brain, including principles such as nonlinear feature maps and pooling of inputs, which were themselves derived from observations from neurophysiological studies in animals (Battleday et al., 2021; Fukushima, 1980; Hubel & Wiesel, 1962; Mozer, 1987; Riesenhuber & Poggio, 1999).”
Automated Seismic Source Characterization Using Deep Graph Neural Networks
van den Ende, M., & Ampuero, J. (2020) · Geophysical Research Letters · doi:10.1029/2020gl088690 · Cited by 176
Deep Convolutional Neural Networks: Structure, Feature Extraction and Training
Namatēvs, I. (2017) · Information Technology and Management Science · doi:10.1515/itms-2017-0007 · Cited by 160
A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex
Hawkins, J., Lewis, M., Klukas, M., Purdy, S., & Ahmad, S. (2019) · Frontiers in Neural Circuits · doi:10.3389/fncir.2018.00121 · Cited by 198
A History of Artificial Intelligence
Grzybowski, A. E., Pawlikowska‐Łagód, K., & Lambert, W. C. (2024) · Clinics in Dermatology · doi:10.1016/j.clindermatol.2023.12.016 · Cited by 191
The implementation of visual routines
Roelfsema, P. R., Lamme, V. A. F., & Spekreijse, H. (2000) · Vision Research · doi:10.1016/s0042-6989(00)00004-3 · Cited by 162
Higgins, I., Chang, L., Langston, V., Hassabis, D., Summerfield, C., Tsao, D., & Botvinick, M. (2021) · Nature Communications · doi:10.1038/s41467-021-26751-5 · Cited by 162
Bubba, T. A., Kutyniok, G., Lassas, M., März, M., Samek, W., Siltanen, S., & Srinivasan, V. (2019) · Inverse Problems · doi:10.1088/1361-6420/ab10ca · Cited by 127
Zhao, Z., Deng, Y., Zhang, Y., Zhang, Y., Zhang, X., & Shao, L. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-019-1007-5 · Cited by 181
On the road to explainable AI in drug-drug interactions prediction: A systematic review
Vo, T. H., Nguyen, N. T. K., Kha, Q. H., & Le, N. Q. K. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.04.021 · Cited by 178
“CNN, which was inspired by the pattern of the animal Visual Cortex [103], has been introduced as an effective approach to deal with data with a grid pattern.”
MethodPattern recognition by labeled graph matching
von der Malsburg, C. (1988) · Neural Networks · doi:10.1016/0893-6080(88)90016-0 · Cited by 162
Chen, Y., Huang, D., Zhang, D., Zeng, J., Wang, N., Zhang, H., & Yan, J. (2021) · Journal of Computational Physics · doi:10.1016/j.jcp.2021.110624 · Cited by 183
Understanding Vision: Theory, Models, and Data
Zhaoping, L. (2014) · doi:10.1093/acprof:oso/9780199564668.001.0001 · Cited by 189
Caigny, A. D., Coussement, K., Bock, K. W. D., & Lessmann, S. (2019) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2019.03.029 · Cited by 177
Raman spectroscopy analysis of number of layers in mass-produced graphene flakes
Silva, D. L., Campos, J. L. E., Fernandes, T. F. D., Rocha, J. N., Machado, L. R. P., Soares, E. M., Miquita, D. R., de Miranda, H. L. S., Rabelo, C., Neto, O. P. V., et al. (2020) · Carbon · doi:10.1016/j.carbon.2020.01.050 · Cited by 160
Convolutional neural networks for crowd behaviour analysis: a survey
Tripathi, G., Singh, K., & Vishwakarma, D. K. (2018) · The Visual Computer · doi:10.1007/s00371-018-1499-5 · Cited by 168
“Earliestworks onCNNshave been reported in [9] andhave been applied tomedical image analysis in 1995 [10].”
MethodCavanagh, P. (2011) · Vision Research · doi:10.1016/j.visres.2011.01.015 · Cited by 201
Prediction of tunnel boring machine operating parameters using various machine learning algorithms
Xu, C. G., Liu, X., Wang, E., & Wang, S. (2020) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2020.103699 · Cited by 163
The third AI summer: AAAI Robert S. Engelmore Memorial Lecture
Kautz, H. (2022) · AI Magazine · doi:10.1002/aaai.12036 · Cited by 258
Artificial neural networks in manufacturing: concepts, applications, and perspectives
Huang, S.-Y., & Zhang, H. (1994) · IEEE Transactions on Components Packaging and Manufacturing Technology Part A · doi:10.1109/95.296402 · Cited by 169
Bayraktar, Y., & Ayan, E. (2021) · Clinical Oral Investigations · doi:10.1007/s00784-021-04040-1 · Cited by 183
Deep networks for system identification: A survey
Pillonetto, G., Aravkin, A. Y., Gedon, D., Ljung, L., Ribeiro, A. H., & Schön, T. B. (2024) · Automatica · doi:10.1016/j.automatica.2024.111907 · Cited by 210
Perceptual grouping and the interactions between visual cortical areas
Murray, S. O., Schrater, P., & Kersten, D. (2004) · Neural Networks · doi:10.1016/j.neunet.2004.03.010 · Cited by 167
“Theories of visual processing have traditionally emphasized a feedforward hierarchical structure, with earlier areas providing feature representations of increasing abstraction sequentially to higher areas (e.g. Fukushima, 1980; Mel, 1997; Riesenhuber & Poggio, 1999; Selfridge, 1958).”
BackgroundThe strong gravitational lens finding challenge
Metcalf, R. B., Meneghetti, M., Avestruz, C., Bellagamba, F., Bom, C. R., Bertin, E., Cabanac, R., Courbin, F., Davies, A., Decencière, E., et al. (2019) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201832797 · Cited by 152
“A CNN (Fukushima 1980; LeCun et al. 1998) is a multi-layer feed-forward neural network model, which is particularly well-suited for processing natural images.”
BackgroundMethodNeural Representations for Object Perception: Structure, Category, and Adaptive Coding
Kourtzi, Z., & Connor, C. E. (2011) · Annual Review of Neuroscience · doi:10.1146/annurev-neuro-060909-153218 · Cited by 153
“Computational models (Fukushima 1980, Riesenhuber & Poggio 1999, Ullman & Soloviev 1999) propose that the brain builds these robust object representations using neuronal connections that group together similar image features across image transformations.”
Wang, F., Zhai, Z., Liu, B., Zheng, S., Zhao, Z., & Chen, X. (2023) · Journal of Energy Storage · doi:10.1016/j.est.2023.109884 · Cited by 164
Self-organization for object extraction using a multilayer neural network and fuzziness measures
Ghosh, A. K., Pal, N. R., & Pal, S. K. (1993) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.1993.390285 · Cited by 160
Critical features for the recognition of biological motion
Casile, A., & Giese, M. A. (2005) · Journal of Vision · doi:10.1167/5.4.6 · Cited by 158
“tions xk within its receptive field using a maximum operator (Fukushima, 1980; Riesenhuber & Poggio, 1999).”
MethodClassifiers for Ischemic Stroke Lesion Segmentation: A Comparison Study
Maier, O., Schröder, C., Forkert, N. D., Martinetz, T., & Handels, H. (2015) · PLOS ONE · doi:10.1371/journal.pone.0145118 · Cited by 150
“In order to achieve a good generalization, a high training sample count, the convolutional architecture [30] and dropout layers [31] are recommended.”
BackgroundThe representation of information about faces in the temporal and frontal lobes
Rolls, E. T. (2006) · Neuropsychologia · doi:10.1016/j.neuropsychologia.2006.04.019 · Cited by 160
Empiricism without magic: transformational abstraction in deep convolutional neural networks
Buckner, C. (2018) · Synthese · doi:10.1007/s11229-018-01949-1 · Cited by 149
Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
Fluke, C. J., & Jacobs, C. (2020) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1349 · Cited by 149
“Artificial neural networks [ANNs; Rosenblatt, 1957, Fukushima, 1980] are the key technique behind the recent AI boom, but date back to the 1950s.”
BackgroundDeep learning for video classification and captioning
Wu, Z., Yao, T., Fu, Y., & Jiang, Y.-G. (2017) · doi:10.1145/3122865.3122867 · Cited by 174
“Inspired by the visual perception mechanisms of animals [30] and McCulloch-Pitts Model [53], Fukushima proposed the “neocognitron” in 1980, which is the first computational model of using local connectivities between neurons of a hierarchically transformed image [16].”
BackgroundEnd-to-end prediction of weld penetration: A deep learning and transfer learning based method
Jiao, W., Wang, Q., Cheng, Y., & Zhang, Y. (2020) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2020.01.044 · Cited by 150
Learning Functions: When Is Deep Better Than ShallowPreprint
Mhaskar, H. N., Liao, Q., & Poggio, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.00988 · Cited by 170
“Fukushima’s Neocognitron(Fukushima, 1980) was a convolutional neural network that was trained to recognize characters.”
BackgroundAutomatic recognition of landslide based on CNN and texture change detection
Ding, A., Zhang, Q., Zhou, X., & Dai, B. (2016) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac.2016.7804935 · Cited by 148
“Kunihiko Fukushima [4] proposed the predecessor of CNN, whose name is “Neocognitron”.”
BackgroundA Brief Survey of Machine Learning and Deep Learning Techniques for E-Commerce Research
Zhang, X., Guo, F., Chen, T., Pan, L., Beliakov, G., & Wu, J. (2023) · Journal of Theoretical and Applied Electronic Commerce Research · doi:10.3390/jtaer18040110 · Cited by 121
Total least mean squares algorithm
Feng, D., Bao, Z., & Jiao, L. (1998) · IEEE Transactions on Signal Processing · doi:10.1109/78.705421 · Cited by 148
Wildfire detection using transfer learning on augmented datasets
Sousa, M. J., Moutinho, A., & Almeida, M. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.112975 · Cited by 158
Convolutional neural networks for brain tumour segmentation
Bhandari, A., Koppen, J., & Agzarian, M. (2020) · Insights into Imaging · doi:10.1186/s13244-020-00869-4 · Cited by 165
Recent advances in plant disease severity assessment using convolutional neural networks
Shi, T., Liu, Y., Zheng, X., Hu, K., Huang, H. M., Liu, H., & Huang, H. (2023) · Scientific Reports · doi:10.1038/s41598-023-29230-7 · Cited by 172
“CNN is a subset of deep learning that first appeared in the 1980s 17 .”
BackgroundGroumpos, P. P. (2023) · Artificial Intelligence and Applications · doi:10.47852/bonviewaia3202689 · Cited by 196
Rosenholtz, R., Huang, J., & Ehinger, K. A. (2012) · Frontiers in Psychology · doi:10.3389/fpsyg.2012.00013 · Cited by 141
“They then build up progressively more complex features by looking for co-occurrence of simple structures over a small pooling region (Fukushima, 1980; Riesenhuber and Poggio, 1999; Deco and Rolls, 2004).”
Backgroundde Vitry, M. M., Kramer, S., Wegner, J. D., & Leitão, J. P. (2019) · Hydrology and earth system sciences · doi:10.5194/hess-23-4621-2019 · Cited by 155
Morphology and gene expression profiling provide complementary information for mapping cell state
Way, G. P., Natoli, T. E., Adeboye, A., Litichevskiy, L., Yang, A. X., Lü, X., Caicedo, J. C., Cimini, B. A., Karhohs, K. W., Logan, D. J., et al. (2022) · Cell Systems · doi:10.1016/j.cels.2022.10.001 · Cited by 178
A model of the ventral visual system based on temporal stability and local memory
Wyss, R., König, P., & Verschure, P. F. M. J. (2006) · PLoS Biology · doi:10.1371/journal.pbio.0040120 · Cited by 145
“In recent years, different models of the ventral visual system have been proposed that aim to account for these properties [”
BackgroundDeep learning in ophthalmology: a review
Grewal, P. S., Oloumi, F., Rubin, U., & TENNANT, M. T. S. (2018) · Canadian Journal of Ophthalmology · doi:10.1016/j.jcjo.2018.04.019 · Cited by 162
A Comprehensive Survey on Geometric Deep Learning
Cao, W., Yan, Z., He, Z., & He, Z. (2020) · IEEE Access · doi:10.1109/access.2020.2975067 · Cited by 180
Bottom-up and top-down computations in word- and face-selective cortex
Kay, K., & Yeatman, J. D. (2017) · eLife · doi:10.7554/elife.22341 · Cited by 158
“This conclusion is consistent with classic hierarchical theories of visual cortex (Fukushima, 1980; Heeger et al., 1996; Serre et al., 2007; DiCarlo et al., 2012; Rolls, 2012) and recent evidence that visual features may explain semantic representations found in high-level visual cortex (Jozwik et…”
MethodResultArtificial intelligence in OCT angiography
Hormel, T. T., Hwang, T. S., Bailey, S. T., Wilson, D. J., Huang, D., & Jia, Y. (2021) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2021.100965 · Cited by 151
Analysis of the process of visual pattern recognition by the neocognitron
Fukushima, K. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90041-5 · Cited by 144
Self-citationUsing Biologically Inspired Features for Face Processing
Meyers, E. M., & Wolf, L. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-007-0058-8 · Cited by 143
“This model follows a similar structure as the classic Neocognitron model ( Fukushima 1980 ), with alternating layers of simple (S) and complex (C) cell units creating increasing complexity as the layers progress from V1 to inferior temporal cortex (IT).”
MethodLSTM and GRU type recurrent neural networks in model predictive control: A Review
Ławryńczuk, M., & Zarzycki, K. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129712 · Cited by 176
The Adaptive Self-Organization of Serial Order in Behavior: Speech, Language, And Motor Control
Grossberg, S. (1987) · Advances in psychology · doi:10.1016/s0166-4115(08)61766-5 · Cited by 143
Deep Learning for Medical Image Segmentation
Lai, M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.02000 · Cited by 85
“Convolutional neural networks are inspired by the observation that for inputs like images (with each pixel being an input dimension), many low level operations are local, and they are not positiondependent [17].”
BackgroundInfluentialMC-LSTM: Mass-Conserving LSTMPreprint
Hoedt, P.-J., Kratzert, F., Klotz, D., Halmich, C., Holzleitner, M., Nearing, G., Hochreiter, S., & Klambauer, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05186 · Cited by 216
“One of the greatest success stories of deep learning are Convolutional Neural Networks (CNNs) (Fukushima, 1980; LeCun & Bengio, 1998; Schmidhuber, 2015; LeCun et al., 2015), whose proficiency can be attributed to their strong inductive bias toward visual tasks (Cohen & Shashua, 2017; Gaier & Ha, 2019).”
BackgroundPredicting the visual world: silence is golden
Koch, C., & Poggio, T. (1999) · Nature Neuroscience · doi:10.1038/4511 · Cited by 141
EEG-Based Emotion Recognition Using Hierarchical Network With Subnetwork Nodes
Yang, Y., Wu, Q. M. J., Zheng, W.-L., & Lu, B.-L. (2018) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2017.2685338 · Cited by 141
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.