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 801–900 of 1,028
Chen, D., Li, X., & Li, S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3105384 · Cited by 94
“CNN is also a kind of metaheuristic algorithm, that is, a multilayer artificial neural network constructed by simulating biological vision systems [40].”
Vehicle Detection in Satellite Images by Parallel Deep Convolutional Neural Networks
Chen, X., Xiang, S., Liu, C.-L., & Pan, C.-H. (2013) · 2013 2nd IAPR Asian Conference on Pattern Recognition · doi:10.1109/acpr.2013.33 · Cited by 79
Learning invariant object recognition in the visual system with continuous transformations
Stringer, S. M., Perry, G., Rolls, E. T., & Proske, J. H. (2005) · Biological Cybernetics · doi:10.1007/s00422-005-0030-z · Cited by 89
“plausible ways of forming invariant representations of stimuli have been studied by a number of investigators (Riesenhuber and Poggio 1999; Fukushima 1980).”
BackgroundMethodHamker, F. H. (2005) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2004.09.005 · Cited by 88
“In parallel architectures translation invariant object recognition could be solved in a hierarchical fashion [97–99].”
BackgroundAn Integrated Approach of Belief Rule Base and Deep Learning to Predict Air Pollution
Kabir, S., Islam, R. U., Hossain, M. S., & Andersson, K. (2020) · Sensors · doi:10.3390/s20071956 · Cited by 78
“It resembles the structure of animal visual cortex [34,35].”
BackgroundMultivariate Time-Series Modeling for Forecasting Sintering Temperature in Rotary Kilns Using DCGNet
Zhang, X., Lei, Y., Chen, H., Zhang, L., & Zhou, Y. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3022019 · Cited by 78
“(CNN) [13] has been widely used in image processing and action recognition due to the unique ability of these networks to”
MethodLong short-term memory suggests a model for predicting shale gas production
Yang, R., Liu, X., Yu, R., Hu, Z., & Duan, X. (2022) · Applied Energy · doi:10.1016/j.apenergy.2022.119415 · Cited by 78
LabGym: Quantification of user-defined animal behaviors using learning-based holistic assessment
Hu, Y., Ferrario, C. R., Maitland, A. D., Ionides, R. B., Ghimire, A., Watson, B. O., Iwasaki, K., White, H., Xi, Y., Zhou, J., et al. (2023) · Cell Reports Methods · doi:10.1016/j.crmeth.2023.100415 · Cited by 101
Handwriting Arabic character recognition LeNet using neural network.
Al-Jawfi, R. A. (2009) · Cited by 78
Learning and Transferring Convolutional Neural Network Knowledge to Ocean Front Recognition
Lima, E. B., Sun, X., Dong, J., Wang, H., Yang, Y., & Liu, L. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2016.2643000 · Cited by 78
“The idea of CNNs was first proposed by Fukushima [10].”
BackgroundVideo scene analysis: an overview and challenges on deep learning algorithms
Abbas, Q., Ibrahim, M. E. A., & Jaffar, M. A. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5438-7 · Cited by 85
“The modern development in the arena has been initiated by the development of deep learning techniques [21, 95, 104], prompted by the improvement of parallel computing hardware and software.”
BackgroundChallenges to pooling models of crowding: Implications for visual mechanisms
Rosenholtz, R. E., Yu, D., & Keshvari, S. (2019) · Journal of Vision · doi:10.1167/19.7.15 · Cited by 90
“This is an attractive and rather intuitive idea, at first glance, because it parallels standard models of object recognition (e.g., Fukushima, 1980; Riesenhuber & Poggio, 1999).”
Residual Networks are Exponential Ensembles of Relatively Shallow Networks.Preprint
Veit, A., Wilber, M. J., & Belongie, S. (2016) · arXiv (Cornell University) · Cited by 78
Gossip training for deep learning
Blot, M., Picard, D., Cord, M., & Thome, N. (2016) · arXiv · doi:10.48550/arxiv.1611.09726 · Cited by 77
“With deep convolutional neural networks (CNN) introduced by [8] and [13], computer vision tasks and more specifically image classification have made huge improvements last few years following [12].”
BackgroundNon-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks
He, X., Yang, S., Li, G., Li, H., Chang, H., & Yu, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018417 · Cited by 92
“Although stacked convolution operations are capable of capturing long-range dependencies by enlarging receptive fields (Fukushima 1980; Lecun et al. 1989), they increase the difficulty of optimization and may face the problem of gradient vanishing.”
Convolutional neural networks with fractional order gradient method
Sheng, D., Wei, Y., Chen, Y., & Wang, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.017 · Cited by 77
“Based on visual cortex, Fukushima designed the neural networks named ’neocognitron’ which is regarded as the origin of CNN [2].”
Renewable energy stocks forecast using Twitter investor sentiment and deep learning
Herrera, G. P., Constantino, M., Su, J., & Naranpanawa, A. (2022) · Energy Economics · doi:10.1016/j.eneco.2022.106285 · Cited by 77
A newcomer’s guide to deep learning for inverse design in nano‐photonics
Khaireh-Walieh, A., Langevin, D., Bennet, P., Teytaud, O., Moreau, A., & Wiecha, P. R. (2023) · Nanophotonics · doi:10.1515/nanoph-2023-0527 · Cited by 93
Invariant visual object recognition: A model, with lighting invariance
Rolls, E. T., & Stringer, S. M. (2006) · Journal of Physiology-Paris · doi:10.1016/j.jphysparis.2006.09.004 · Cited by 83
“In this section we address two key issues that arise in hierarchical layered network architectures, such as VisNet, other examples of which have been described and analyzed by Fukushima (1980), Ackley et al. (1985), and Rosenblatt (1961).”
BackgroundMethodInfluentialRust, N. C., & DiCarlo, J. J. (2012) · The Journal of Neuroscience · doi:10.1523/jneurosci.6125-11.2012 · Cited by 79
“We also know that some of the leading “feedforward” style computational models of the ventral visual stream use strategies that either explicitly (Fukushima, 1980; Riesenhuber and Poggio, 1999; Serre et al., 2007) or implicitly (LeCun et al., 2004; Pinto et al., 2009) attempt to balance and-like…”
BackgroundDeep learning classification in asteroseismology
Hon, M., Stello, D., & Yu, J. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx1174 · Cited by 77
“These are machine learning methods that mimic biological neuron structures, aimed towards feature detection in data (Fukushima 1980).”
MethodPerceptual straightening of natural videos
Hénaff, O. J., Goris, R. L. T., & Simoncelli, E. P. (2019) · Nature Neuroscience · doi:10.1038/s41593-019-0377-4 · Cited by 127
Strategies to Improve the Accuracy of Memristor-Based Convolutional Neural Networks
Pan, W.-Q., Chen, J., Kuang, R., Li, Y., He, Y.-H., Feng, G.-R., Duan, N., Chang, T.-C., & Miao, X.-S. (2020) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2019.2963323 · Cited by 76
“for neuromorphic computing have been demonstrated in recent years, such as multilayer perception (MLP) network [1], convolutional neural network (CNN) [5], spiking neural network (SNN) [6], and long short-term memory (LSTM) network [7].”
BackgroundLearning-based Memory Allocation for C++ Server Workloads
Maas, M., Andersen, D. G., Isard, M., Javanmard, M. M., McKinley, K. S., & Raffel, C. (2020) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3373376.3378525 · Cited by 76
“In contrast, feed-forward neural networks like multi-layer perceptrons [23] or convolutional neural networks [20, 39] can recognize local patterns, but require some form of temporal integration in order to apply them to variable-length sequences.”
MethodA novel attentional deep neural network-based assessment method for ECG quality
Jin, Y., Li, Z., Qin, C., Liu, J., Liu, Y., Zhao, L., & Liu, C. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104064 · Cited by 86
Detecting People in Artwork with CNNs
Westlake, N., Cai, H., & Hall, P. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46604-0_57 · Cited by 95
“Deep learning has been around for a few decades [7,8,9].”
BackgroundWhen Ensemble Learning Meets Deep Learning: a New Deep Support Vector Machine for Classification
Qi, Z., Wang, B., Tian, Y., & Zhang, P. (2016) · Knowledge-Based Systems · doi:10.1016/j.knosys.2016.05.055 · Cited by 76
'Artiphysiology' reveals V4-like shape tuning in a deep network trained for image classification
Pospisil, D. A., Pasupathy, A., & Bair, W. (2018) · eLife · doi:10.7554/elife.38242 · Cited by 91
“Thus, while CNN architecture is often associated with translation invariance ( Fukushima, 1980 ; Rumelhart et al., 1986 ; Riesenhuber and Poggio, 1999 ; Serre et al., 2005 ; Cadieu et al., 2007 ; Goodfellow et al., 2009 ; Lenc and Vedaldi, 2014 ), we find that high TI for actual single unit…”
BackgroundComputational Foundations of Natural Intelligence
van Gerven, M. A. J. (2017) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2017.00112 · Cited by 91
“Deep architectures have been used extensively in neuroscience to model hierarchical processing (Selfridge, 1959; Fukushima, 1980; Riesenhuber and Poggio, 1999; Fukushima, 2013; Lehky and Tanaka, 2016).”
MethodBai, Y., Xiong, Y., Huang, J., Zhou, J., & Zhang, B. (2019) · Postharvest Biology and Technology · doi:10.1016/j.postharvbio.2019.110943 · Cited by 77
On Catastrophic Forgetting and Mode Collapse in Generative Adversarial NetworksPreprint
Thanh-Tung, H., & Tran, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.04015 · Cited by 88
CNN and RNN mixed model for image classification
Yin, Q., Zhang, R., & Shao, X. (2019) · MATEC Web of Conferences · doi:10.1051/matecconf/201927702001 · Cited by 75
Entity-aware Image Caption Generation
Lu, D., Whitehead, S., Huang, L., Ji, H., & Chang, S. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1435 · Cited by 75
Monarch Butterfly Optimization Based Convolutional Neural Network Design
Bačanin, N., Bezdan, T., Tuba, E., Strumberger, I., & Tuba, M. (2020) · Mathematics · doi:10.3390/math8060936 · Cited by 77
“The first example of an artificial neural network model, the Neocognitron, was introduced by Fukushima in 1980 [10].”
BackgroundTexture-like representation of objects in human visual cortex
Jagadeesh, A. V., & Gardner, J. L. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2115302119 · Cited by 91
On invariance and selectivity in representation learning
Anselmi, F., Rosasco, L., & Poggio, T. (2016) · Information and Inference · doi:10.1093/imaiai/iaw009 · Cited by 51
Cowell, R. A., Bussey, T. J., & Saksida, L. M. (2009) · Journal of Cognitive Neuroscience · doi:10.1162/jocn.2009.21373 · Cited by 79
Paul, R., Hawkins, S. H., Hall, L., Goldgof, D. B., & Gillies, R. J. (2016) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2016.7844626 · Cited by 75
“[5] Fukushima, Kunihiko.”
BackgroundBarnard, E., & Casasent, D. P. (1991) · IEEE Transactions on Neural Networks · doi:10.1109/72.134287 · Cited by 75
Spontaneous Facial Expression Recognition: A Part Based Approach
Perveen, N., Singh, D., & Mohan, C. K. (2016) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2016.0147 · Cited by 76
“The reason for choosing the CNN as the feature extraction mechanism is that it can handle the translation and scale variances, and therefore scaling and translation issues can be resolved to some extent [31].”
BackgroundOn the application of reservoir computing networks for noisy image recognition
Jalalvand, A., Demuynck, K., Neve, W. D., & Martens, J. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.11.100 · Cited by 84
“Thanks to the advances in the structure of the neural networks since the early 80’s, such as introducing the concept of Deep Neural Networks (DNNs) [1, 2] and Convolutional Neural Network (CNN) [3] along with the more powerful computational hardware, image processing have become more elegant than ever.”
BackgroundApplication and Construction of Deep Learning Networks in Medical Imaging
Torres-Velázquez, M., Chen, W., Li, X., & McMillan, A. B. (2020) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2020.3030611 · Cited by 83
“Inspired by Hubel and Wiesel’s work [17]–[19], Fukushima [20] invented the neocognitron network in 1980 based on the previous work, the cognitron [21].”
MethodInterest Point Detector and Feature Descriptor Survey
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_6 · Cited by 80
Deep Learning with Dynamic Spiking Neurons and Fixed Feedback Weights
Samadi, A., Lillicrap, T., & Tweed, D. (2017) · Neural Computation · doi:10.1162/neco_a_00929 · Cited by 74
Small sample image recognition using improved Convolutional Neural Network
Zhang, J., Shao, K., & Luo, X. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.07.011 · Cited by 74
Spike detection and sorting with deep learning
Rácz, M., Liber, C., Németh, E., Fiáth, R., Rokai, J., Harmati, I., Ulbert, I., & Márton, G. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab4896 · Cited by 78
“Convolutional neural networks Convolutional neural networks (CNNs) [39] are neural networks containing convolutional layers that store the representation of the data in the form of convolutional filters.”
BackgroundDeep Neural Networks in Computational NeurosciencePreprint
Kietzmann, T. C., McClure, P., & Kriegeskorte, N. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/133504 · Cited by 108
“The need for multiple stages of nonlinear computation has long been appreciated in the domain of vision, by both experimentalists (Hubel & Wiesel, 1959) and theorists (Fukushima, 1980; Lecun & Bengio, 1995; Riesenhuber & Poggio, 1999; G. Wallis & Rolls, 1997).”
BackgroundLearning strides in convolutional neural networksPreprint
Riad, R., Teboul, O., Grangier, D., & Zeghidour, N. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/4yz8f · Cited by 90
Using deep learning for mammography classification
Hepsağ, P. U., Özel, S. A., & Yazıcı, A. (2017) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk.2017.8093429 · Cited by 73
Li, G., & Li, N. (2019) · Electronic Commerce Research · doi:10.1007/s10660-019-09334-x · Cited by 82
Machine learning for recognizing minerals from multispectral data
Jahoda, P., Drozdovskiy, I., Payler, S. J., Turchi, L., Bessone, L., & Sauro, F. (2020) · The Analyst · doi:10.1039/d0an01483d · Cited by 80
Guo, A., Pasque, M. K., Loh, F. E., Mann, D. L., & Payne, P. (2020) · Current Epidemiology Reports · doi:10.1007/s40471-020-00259-w · Cited by 73
“Moreover, deep learning models, like deep belief neural networks [9], deep convolutional networks [10], and long short-term memory [11] models, as well as more complicated deep learning models, have for the most part demonstrated stronger prediction and classification capability than traditional…”
BackgroundUnderstanding adversarial examples requires a theory of artefacts for deep learning
Buckner, C. J. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00266-y · Cited by 90
Learning Lie Groups for Invariant Visual Perception
Rao, R. P. N., & Ruderman, D. (1998) · Cited by 72
Fan, X., Li, J., Li, X., Zhong, Y., & Cao, J. (2019) · Science China Physics Mechanics and Astronomy · doi:10.1007/s11433-018-9321-7 · Cited by 74
New method to observe gravitational waves emitted by core collapse supernovae
Astone, P., Cerdá-Durán, P., Palma, I. D., Drago, M., Muciaccia, F., PALOMBA, C., & Ricci, F. (2018) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.98.122002 · Cited by 80
Neural networks as cybernetic systems
Cruse, H. (1996) · Cited by 83
A Survey on Deep Learning Methods for Robot VisionPreprint
Ruíz-del-Solar, J., Loncomilla, P., & Soto, N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.10862 · Cited by 86
“In 1980, Fukushima proposed the NeoCognitron [4], a multilayered neural network inspired by the seminal studies of the mammalian visual system of Hubel and Wiesel [3].”
BackgroundInfluentialThe CNN as a Guided Multilayer RECOS Transform [Lecture Notes]
Kuo, C. ‐. J. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2671158 · Cited by 72
“Furthermore, the CNN self-organization capability was well discussed in the 1980s and 1990s, e.g., [6].”
BackgroundSaxena, D., & Raychoudhury, V. (2017) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2017.2723843 · Cited by 72
“Classification algorithms are neural network (NN) [44], support vector machine (SVM) [45], Naïve Bayes (NB) [46], K-nearest neighbor (KNN) [47], discriminant analysis (DA) [48], generalized linear model [logistic regression (LR)] [49], decision tree (DT) [50], and ensembles (AdaBoost (Ada) [51] and TreeBagger (TB) [52…”
BackgroundAn Investigation of 3D Human Pose Estimation for Learning Tai Chi: A Human Factor Perspective
Kamel, A., Liu, B., Li, P., & Sheng, B. (2018) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2018.1543081 · Cited by 74
“The prototype of CNN first appeared in the 1980s (Fukushima, 1980; Rumelhart, Hinton, & Williams, 1986).”
BackgroundRobust Cherry Tomatoes Detection Algorithm in Greenhouse Scene Based on SSD
Yuan, T., Lv, L., Zhang, F., Fu, J., Gao, J. G., Zhang, J., Li, W., Zhang, C., & Zhang, W. (2020) · Agriculture · doi:10.3390/agriculture10050160 · Cited by 72
“[11] proposed AlexNet convolutional neural network (CNN [12]) architecture, which avioded the complicated feature engineering and reduced the requirements of image preprocessing.”
BackgroundQadeer, K., Rehman, W. U., Sheri, A. M., Park, I., Kim, H. K., & Jeon, M. (2020) · Applied Sciences · doi:10.3390/app10113984 · Cited by 77
“CNNLSTM is also a variant of LSTM models in which CNN [24] has been used for extracting the features and then fed to the LSTM model to get the forecast; they are being used in various time series prediction problems [25,26].”
MethodResNet50-Based Effective Model for Breast Cancer Classification Using Histopathology Images
Behar, N., & Shrivastava, M. (2021) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2022.017030 · Cited by 74
Kidney Tumor Semantic Segmentation Using Deep Learning: A Survey of State-of-the-Art
Abdelrahman, A., & Viriri, S. (2022) · Journal of Imaging · doi:10.3390/jimaging8030055 · Cited by 81
“It was first released in 1980 [75].”
Mahendrakar, T., Ekblad, A., Fischer, N., White, R. T., Wilde, M., Kish, B. A., & Silver, I. M. (2022) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero53065.2022.9843537 · Cited by 86
“LeCun et al. [18] drew on models of the mammalian visual cortex by Hubel and Wiesel [19] and a new neural architecture by Fukushima [20] to propose an approach unifying neural networks with classical computer vision: the convolutional neural network (CNN).”
MethodArslan, B., Nuhoğlu, Ç., Satıcı, M. O., & Altınbilek, E. (2024) · The American Journal of Emergency Medicine · doi:10.1016/j.ajem.2024.12.024 · Cited by 75
Deep Learning for Sustainable Aquaculture: Opportunities and Challenges
Wu, A.-Q., Li, K.-L., Song, Z.-Y., Lou, X., Hu, P., Yang, W., & Wang, R.-F. (2025) · Sustainability · doi:10.3390/su17115084 · Cited by 81
Hadweh, P., Niset, A., Salvagno, M., Barajraji, M. A., Hadwe, S. E., Taccone, F. S., & Barrit, S. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14124026 · Cited by 85
An Introduction to Neural Networks
Aggarwal, C. C. (2018) · Springer eBooks · doi:10.1007/978-3-319-94463-0_1 · Cited by 87
Learning in the machine: Random backpropagation and the deep learning channel
Baldi, P., Sadowski, P., & Lu, Z. (2018) · Artificial Intelligence · doi:10.1016/j.artint.2018.03.003 · Cited by 75
“Note that Hebbian learning [15] is a form of local learning, and deep local learning has been proposed for instance by Fukushima [10] to train the neocognitron architecture, essentially a feed forward convolutional neural network inspired by the earlier neurophysiological work of Hubel and Wiesel [18].”
MethodAutomatic identification for field butterflies by convolutional neural networks
Almryad, A. S., & Kutucu, H. (2020) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2020.01.006 · Cited by 73
Feature-specific neural reactivation during episodic memory
Bone, M. B., Ahmad, F. N., & Buchsbaum, B. R. (2020) · Nature Communications · doi:10.1038/s41467-020-15763-2 · Cited by 75
Spiking Neural Networks: Background, Recent Development and the NeuCube Architecture
Tan, C. N. W., Šarlija, M., & Kasabov, N. K. (2020) · Neural Processing Letters · doi:10.1007/s11063-020-10322-8 · Cited by 77
The use of artificial intelligence and robotics in regional anaesthesia
McKendrick, M., Yang, S., & McLeod, G. A. (2021) · Anaesthesia · doi:10.1111/anae.15274 · Cited by 72
“The discovery in 1962 by Hubel and Wiesel [9] that the transmission of visual information from the retina to the brain was attributed to multilevel receptive fields inspired Fukushima to design a multilayered neural network named “Neocognitron” [10].”
BackgroundChen, L., Yan, H., Yan, J., Wang, J., Tao, T., Xin, K., Li, S., Pu, Z., & Qiu, J. (2022) · Journal of Hydrology · doi:10.1016/j.jhydrol.2022.127440 · Cited by 74
Bai, X., & Stede, M. (2023) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-022-00323-0 · Cited by 55
Beniwal, M., Singh, A., & Kumar, N. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107617 · Cited by 71
Deep learning for hyperspectral image classification: A comprehensive review and future predictions
Song, Y., Zhang, J., Liu, Z., Xu, Y., Quan, S., Sun, L., Bi, J., & Wang, X. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103285 · Cited by 82
When Deep Learning Meets Polyhedral Theory: A Survey
Huchette, J., Muñoz, G., Serra, T., & Tsay, C. (2026) · INFORMS journal on computing · doi:10.1287/ijoc.2024.0902 · Cited by 82
On Real-Time AER 2-D Convolutions Hardware for Neuromorphic Spike-Based Cortical Processing
Serrano-Gotarredona, R., Serrano‐Gotarredona, T., Acosta, A. J., Serrano, C., Pérez‐Carrasco, J. A., Linares-Barranco, B., Linares-Barranco, A., Jiménez, G., & Civit, A. (2008) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2000163 · Cited by 71
“Software convolution neural networks have been successfully applied for character recognition [4]–[8], object detection [7], and face recognition [8]–[10].”
BackgroundApplying Deep Learning to Stereotypical Motor Movement Detection in Autism Spectrum Disorders
Rad, N. M., & Furlanello, C. (2016) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2016.0178 · Cited by 71
“The initial idea of CNN was first introduced by Fukushima [18] where a hierarchical multi-layer artificial neural network based on local connectivity between neurons were used for visual pattern recognition.”
BackgroundTrends in deep convolutional neural Networks architectures: a review
Elhassouny, A., & Smarandache, F. (2019) · International Conference of Computer Science and Renewable Energies (ICCSRE) · doi:10.1109/iccsre.2019.8807741 · Cited by 78
“…conclusion is proved by the number of contributions, number of layers, and accuracy error of such algorithms. a) Neocognitron: Fukushima et al. [13]–[15] introduced the notion of neural networks and CNN model for mechanism of pattern recognition, based on some earliest predecessors…”
BackgroundDeng, Q., Wang, J., Hillebrand, K., Benjamin, C. R., & Söffker, D. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2937287 · Cited by 79
“Convolutional neural network (CNN) [15] is a specialized type of artificial neural network and belongs to the subgroup of deep learning techniques.”
BackgroundAccurate detection of myocardial infarction using non linear features with ECG signals
Sridhar, C., Lih, O. S., Jahmunah, V., Koh, J. E. W., Ciaccio, E. J., San, T. R., Arunkumar, N., Kadry, S., & Acharya, U. R. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02536-4 · Cited by 75
Nguyen, C., Sagan, V., Skobalski, J., & Severo, J. I. (2023) · Remote Sensing · doi:10.3390/rs15133301 · Cited by 77
Recognition Algorithms in E-Nose: A Review
Yang, X., Li, M., Ji, X., Chang, J., Deng, Z., & Meng, G. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3302868 · Cited by 77
What your visual system sees where you are not looking
Rosenholtz, R. E. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.876659 · Cited by 77
“They then build up progressively more complex features by looking for co-occurrence of simple structures over a small pooling region.(30,31) These co-occurrences, computed over a larger pooling region, can approximate the correlations computed by our model.”
BackgroundPosition invariant recognition in the visual system with cluttered environments
Stringer, S. M., & Rolls, E. T. (2000) · Neural Networks · doi:10.1016/s0893-6080(00)00017-4 · Cited by 70
Invariant Object Recognition and Pose Estimation with Slow Feature Analysis
Franzius, M., Wilbert, N., & Wiskott, L. (2011) · Neural Computation · doi:10.1162/neco_a_00171 · Cited by 80
“…of invariant object recognition are inspired by this interpretation of the ventral path and implement explicit mechanisms for increasing position invariance (Fukushima, 1980; Wersing & K¨orner, 2003; Rolls & Stringer, 2006), which successfully reduces view dependence of their representations.”
BackgroundA Hierarchical Predictive Coding Model of Object Recognition in Natural Images
Spratling, M. W. (2017) · Cognitive Computation · doi:10.1007/s12559-016-9445-1 · Cited by 66
The Adaptive Self-organization of Serial Order in Behavior: Speech, Language, and Motor Control
Grossberg, S. (1986) · Elsevier eBooks · doi:10.1016/b978-0-12-631403-8.50011-4 · Cited by 71
Liao, W., Coillie, F. V., Gao, L., Li, L., Zhang, B., & Chanussot, J. (2018) · IEEE Access · doi:10.1109/access.2018.2880083 · Cited by 73
“and stacked denoising autoencoders (SDAEs) [43], deep Boltzmann machines (DBMs) [42], convolutional neural networks [44], and deep sparse filters (DSFs) [45].”
BackgroundAP-Net: An atomic-pairwise neural network for smooth and transferable interaction potentials
Glick, Z. L., Metcalf, D. P., Koutsoukas, A., Spronk, S. A., Cheney, D. L., & Sherrill, C. D. (2020) · The Journal of Chemical Physics · doi:10.1063/5.0011521 · Cited by 69
Results of the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC)
Hložek, R., Malz, A. I., Ponder, K. A., Dai, M., Narayan, G., Ishida, É. E. O., Allam, T., Bahmanyar, A., Bi, X., Biswas, R., et al. (2023) · The Astrophysical Journal Supplement Series · doi:10.3847/1538-4365/accd6a · Cited by 92
Neural Network–Based Financial Volatility Forecasting: A Systematic Review
Ge, W., Lalbakhsh, P., Isai, L., Lenskiy, A. A., & Suominen, H. (2022) · ACM Computing Surveys · doi:10.1145/3483596 · Cited by 88
“Third, convolutional neural networks (CNNs), originally based on the visual cortex [45], were designed for image tasks, and leverages spatial information in the data.”
MethodHyperspectral Image Classification Based on Fusing S3-PCA, 2D-SSA and Random Patch Network
Chen, H., Wang, T., Chen, T., & Deng, W. (2023) · Remote Sensing · doi:10.3390/rs15133402 · Cited by 69
Curvature Processing Dynamics in Macaque Area V4
Yau, J. M., Pasupathy, A., Brincat, S. L., & Connor, C. E. (2013) · Cerebral Cortex · doi:10.1093/cercor/bhs004 · Cited by 66
“Keywords: neurophysiology, PIT, temporal dynamics, vision”
BackgroundDiscriminative feature extraction from X-ray images using deep convolutional neural networks
Srinivas, M., Roy, D., & Mohan, C. K. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471809 · Cited by 69
“[9] and the architecture was later improved by LeCun et al.”
BackgroundImplementation of deep neural networks to count dopamine neurons in substantia nigra
Penttinen, A., Parkkinen, I., Blom, S., Kopra, J. J., Andressoo, J., Pitkänen, K., Voutilainen, M. H., Saarma, M., & Airavaara, M. (2018) · European Journal of Neuroscience · doi:10.1111/ejn.14129 · Cited by 76
“Convolutional neural networks (CNN) are ANNs that are especially powerful for pattern recognition in digital images (Fukushima, 1980; Lecun, Bottou, Bengio, & Haffner, 1998).”
Background
Metadata
- Authors
- Fukushima, K.
- Affiliations
- Japan Broadcasting Corporation (Japan) (JP)
- Corresponding author
- Fukushima, Kunihiko
- ORCID
- Fukushima, Kunihiko
- Venue
- Biological Cybernetics
- Published
- 1980-04
- Volume
- 36
- Issue
- 4
- Pages
- 193-202
- ISSN
- 0340-1200 (ISSN-L)
- 1432-0770
- OpenAlex
- W613766092
- Semantic Scholar
- 69e68bfaadf2dccff800158749f5a50fe82d173b
- Cited by
- 5,759
- References
- 13
- Citations by year
- 2026: 219 · 2025: 454 · 2024: 494 · 2023: 455 · 2022: 452 · 2021: 544 · 2020: 545 · 2019: 433 · 2018: 301 · 2017: 319 · 2016: 287 · 2015: 176 · 2014: 140 · 2013: 78 · 2012: 71
- FWCI
- 4.02
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Biological Cybernetics (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Life Sciences › Neuroscience › Cognitive Neuroscience › Visual perception and processing mechanisms
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
- Keywords
- neocognitron, visual pattern recognition, unsupervised learning, self-organization, position invariance, S cells, C cells, simple cells, complex cells, hypercomplex cells, visual cortex model, synaptic plasticity, shape recognition
- MeSH terms
- Cognition, Computers, Form Perception, Learning, Models, Neurological, Nerve Net, Nervous System Physiological Phenomena, Pattern Recognition, Visual
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.