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 301–400 of 1,028
Deep Convolutional Neural Networks for Fire Detection in Images
Sharma, J., Granmo, O.-C., Goodwin, M., & Fidje, J. T. (2017) · Communications in Computer and Information Science · doi:10.1007/978-3-319-65172-9_16 · Cited by 259
“The Convolutional Neural Network was first introduced in 1980 by Fukushima [6].”
Acharya, U. R., Fujita, H., Oh, S. L., Raghavendra, U., Tan, J. H., Adam, M., Gertych, A., & Hagiwara, Y. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2017.08.039 · Cited by 277
Brief History of Artificial Intelligence
Muthukrishnan, N., Maleki, F., Ovens, K., Reinhold, C., Forghani, B., & Forghani, R. (2020) · Neuroimaging Clinics of North America · doi:10.1016/j.nic.2020.07.004 · Cited by 229
Double Graph Based Reasoning for Document-level Relation Extraction
Zeng, S., Xu, R., Chang, B., & Li, L. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.127 · Cited by 245
Applications of artificial intelligence in dentistry: A comprehensive review
Carrillo‐Perez, F., Pecho, O. E., Morales, J. C., Paravina, R. D., Della Bona, A., Ghinea, R., Pulgar, R., Pérez, M. D. M., & Herrera, L. J. (2022) · Journal of Esthetic and Restorative Dentistry · doi:10.1111/jerd.12844 · Cited by 251
“Although they were first proposed in 1980, 165 it was not until diverse modifications were applied to the learning algorithms, the quantity of data available was dramatically increased, and the necessary computing platforms were developed, that CNNs were revisited.”
Hirani, R., Noruzi, K., Khuram, H., Hussaini, A. S., Aifuwa, E. I., Ely, K. E., Lewis, J. M., Gabr, A. E., Smiley, A., Tiwari, R. K., et al. (2024) · Life · doi:10.3390/life14050557 · Cited by 210
“Research on CNNs surged in the 1970s, and the first neural networks were already put to clinical use by 1995 [21,22].”
BackgroundA pre-trained convolutional neural network based method for thyroid nodule diagnosis
Ma, J., Wu, F., Zhu, J., Xu, D., & Kong, D. (2017) · Ultrasonics · doi:10.1016/j.ultras.2016.09.011 · Cited by 273
Data-driven science and engineering : machine learning, dynamical systems, and control
Brunton, S. L., & Kutz, J. N. (2019) · doi:10.1017/978-1-009-08951-7 · Cited by 242
Deep reinforcement learning and its neuroscientific implications
Botvinick, M., Wang, J. X., Dabney, W., Miller, K. J., & Kurth-Nelson, Z. (2020) · Neuron · doi:10.1016/j.neuron.2020.06.014 · Cited by 269
“Most deep RL systems that take visual inputs employ a processing architecture (a convolutional network, Fukushima, 1980) that biases them toward representations that take into account the translational invariance of images.”
BackgroundComputational Intelligence: Concepts to Implementations
Eberhart, R. C. (2007) · Cited by 299
Deep Learning: The Good, the Bad, and the Ugly
Serre, T. (2019) · Annual Review of Vision Science · doi:10.1146/annurev-vision-091718-014951 · Cited by 267
Ahmed, I. A., Senan, E. M., Rassem, T. H., Ali, M. A. H., Shatnawi, H. S. A., Alwazer, S. M., & Alshahrani, M. (2022) · Electronics · doi:10.3390/electronics11040530 · Cited by 238
Cnvlutin: Ineffectual-Neuron-Free Deep Neural Network Computing
Albericio, J., Judd, P., Hetherington, T., Aamodt, T., Jerger, N. E., & Moshovos, A. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.11 · Cited by 226
A Brief History of AI: How to Prevent Another Winter (A Critical Review)
Toosi, A., Bottino, A. G., Saboury, B., Siegel, E., & Rahmim, A. (2021) · PET Clinics · doi:10.1016/j.cpet.2021.07.001 · Cited by 191
“The “neocognitron”, the first convolutional neural networks (CNN) architecture, was proposed by Fukushima in 1980 [55].”
BackgroundA neural network approach to cloud classification
Lee, J., Weger, R. C., Sengupta, S. K., & Welch, R. M. (1990) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/36.58972 · Cited by 262
Machine learning in protein structure prediction
AlQuraishi, M. (2021) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2021.04.005 · Cited by 252
Bake off redux: a review and experimental evaluation of recent time series classification algorithms
Middlehurst, M., Schäfer, P., & Bagnall, A. (2024) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-024-01022-1 · Cited by 197
“Convolution Neural Networks (CNN), were first introduced in (Fukushima, 1980), and have gained widespread use in image recognition.”
BackgroundConvolutional Neural Networks for Toxic Comment Classification
Georgakopoulos, S. V., Tasoulis, S. K., Vrahatis, A. G., & Plagianakos, V. P. (2018) · Proceedings of the 10th Hellenic Conference on Artificial Intelligence · doi:10.1145/3200947.3208069 · Cited by 194
“Each of these stages, consist the types of layers described below [6, 15]:”
BackgroundPerrett, D. I., Oram, M. W., & Ashbridge, E. (1998) · Cognition · doi:10.1016/s0010-0277(98)00015-8 · Cited by 254
Ameri, R., Hsu, C.-C., & Band, S. S. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107717 · Cited by 213
Deep-learning-based automatic computer-aided diagnosis system for diabetic retinopathy
Mansour, R. F. (2018) · Biomedical Engineering Letters · doi:10.1007/s13534-017-0047-y · Cited by 250
“Approaches were also developed decades before (1970s) to enable better imaging system and its analysis [5] to assist applications and effectiveness of approaches to solve certain task [6].”
BackgroundDeep learning and radiomics in precision medicine
Parekh, V. S., & Jacobs, M. A. (2019) · Expert Review of Precision Medicine and Drug Development · doi:10.1080/23808993.2019.1585805 · Cited by 246
Detection of brain tumors from MRI images base on deep learning using hybrid model CNN and NADE
Hashemzehi, R., Mahdavi, S. J. S., Kheirabadi, M., & Kamel, S. R. (2020) · Biocybernetics and Biomedical Engineering · doi:10.1016/j.bbe.2020.06.001 · Cited by 236
The gamma model—A new neural model for temporal processing
Vries, B. D., & Principe, J. C. (1992) · Neural Networks · doi:10.1016/s0893-6080(05)80035-8 · Cited by 254
70 years of machine learning in geoscience in review
(2020) · Advances in Geophysics · doi:10.1016/bs.agph.2020.08.002 · Cited by 222
“l and Norvig, 2010]; Kriging: [Krige, 1951]; Decision Trees: [Belson, 1959]; Nearest Neighbours: [Cover and Hart, 1967]; Automatic Differentiation: [Linnainmaa, 1970]; Convolutional Neural Networks: [Fukushima, 1980, LeCun et al., 2015]; Recurrent Neural Networks: [Hopfield, 1982]; Backpropagation: [Kelley, 1960, Bryso…”
Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
Liao, Q., & Poggio, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.03640 · Cited by 168
Pinto, N., Doukhan, D., DiCarlo, J. J., & Cox, D. D. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000579 · Cited by 248
“[1–6]), biologically-inspired models are routinely among the highest-performing artificial vision systems in practical tests of object and face recognition [7–12].”
Bussey, T. J., & Saksida, L. M. (2002) · European Journal of Neuroscience · doi:10.1046/j.0953-816x.2001.01850.x · Cited by 234
“Several models of object processing feature a hierarchical organization of visual representations (e.g. Fukushima, 1980; Perrett & Oram, 1993; Wallis & Rolls, 1997; Riesenhuber & Poggio, 1999).”
BackgroundAutomatic classification of pavement crack using deep convolutional neural network
Li, B., Wang, K. C. P., Zhang, A., Yang, E., & Wang, G. (2020) · International Journal of Pavement Engineering · doi:10.1080/10298436.2018.1485917 · Cited by 239
“Convolutional Neural Network (CNN), introduced in 1980 (Fukushima 1980) and improved over the past two decades (Behnke 2003, Simard et al.”
BackgroundInvariant pattern recognition: A review
Wood, J. (1996) · Pattern Recognition · doi:10.1016/0031-3203(95)00069-0 · Cited by 246
Schneider, S., Taylor, G. W., Linquist, S., & Kremer, S. C. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13133 · Cited by 245
Serre, T., Kouh, M., Cadieu, C. F., Knoblich, U., Kreiman, G., & Poggio, T. (2005) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 275
A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
Srinivas, S., Sarvadevabhatla, R. K., Mopuri, K. R., Prabhu, N., Kruthiventi, S. S. S., & Babu, R. V. (2016) · Frontiers in Robotics and AI · doi:10.3389/frobt.2015.00036 · Cited by 171
ETHOS: a multi-label hate speech detection dataset
Mollas, I., Chrysopoulou, Z., Karlos, S., & Tsoumakas, G. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00608-2 · Cited by 175
“[7], RF, AdaBoost (Ada) [15] and Gradient Boosting (Grad) [16]. Moreover, we used six different NN architectures, as other similar works attempt [31]. The first one utilises convolutional NNs (CNNs) [17] with an attention [4] layer. The second is a compilation of CNNs and long short-term memory NNs (LSTMs) [22]. A sin…”
MethodTimecourse of neural signatures of object recognition
Johnson, J. S., & Olshausen, B. A. (2003) · Journal of Vision · doi:10.1167/3.7.4 · Cited by 235
“…and psychophysical data suggests that recognition is performed so rapidly that it must be accomplished in one feedforward sweep of activity propagated through the visual system (Fukushima, 1980; Mel, 1997; Riesenhuber & Poggio, 1999; VanRullen & Thorpe, 2001a; VanRullen & Thorpe, 2002).”
BackgroundA neural network for visual pattern recognition
Fukushima, K. (1988) · Computer · doi:10.1109/2.32 · Cited by 238
Self-citationThe three ghosts of medical AI: Can the black-box present deliver?
Quinn, T. P., Jacobs, S., Senadeera, M., Le, V., & Coghlan, S. (2022) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102158 · Cited by 215
A Comparison of Discriminant Analysis versus Artificial Neural Networks
Yoon, Y., Swales, G., & Margavio, T. M. (1993) · Journal of the Operational Research Society · doi:10.1057/jors.1993.6 · Cited by 227
Neural Networks and Neuroscience-Inspired Computer Vision
Cox, D. D., & Dean, T. (2014) · Current Biology · doi:10.1016/j.cub.2014.08.026 · Cited by 223
“Meanwhile, neuroscience has provided guiding force for the development of artificial neural networks, providing inspiration for architectural features of neural networks (e.g., simple-to-complex pooling in Fukushima’s neocognitron [29,30]).”
BackgroundCCLearner: A Deep Learning-Based Clone Detection Approach
Li, L., Feng, H., Zhuang, W., Meng, N., & Ryder, B. (2017) · 2017 IEEE International Conference on Software Maintenance and Evolution (ICSME) · doi:10.1109/icsme.2017.46 · Cited by 214
“Deep Neural Networks (DNNs) are neural networks with multiple hidden layers between the input and output layers [18].”
BackgroundGhafoorian, M., Karssemeijer, N., Heskes, T., van Uden, I. W. M., Sanchez, C. I., Litjens, G., de Leeuw, F.-E., van Ginneken, B., Marchiori, E., & Platel, B. (2017) · Scientific Reports · doi:10.1038/s41598-017-05300-5 · Cited by 236
“Deep neural networks 45, 46 are biologically plausible learning structures, inspired by early neuroscience-related work 47, 48 and have so far claimed human level or super-human performances in several different domains 49–53 .”
BackgroundAdversarial Robustness as a Prior for Learned RepresentationsPreprint
Engstrom, L., Ilyas, A., Santurkar, S., Tsipras, D., Tran, B., & Mądry, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.00945 · Cited by 284
A renaissance of neural networks in drug discovery
Baskin, I. I., Winkler, D., & Tetko, I. V. (2016) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2016.1201262 · Cited by 235
“Like deep learning, convolutional ANNs were inspired by the neocognitron [4] architecture for image recognition.”
BackgroundMethodOmnivore: A Single Model for Many Visual Modalities
Girdhar, R., Singh, M., Ravi, N., van der Maaten, L., Joulin, A., & Misra, I. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01563 · Cited by 196
“ConvNet architectures [26, 48] have been popular for many computer vision tasks in images, video, and 3D recognition.”
BackgroundUnsupervised Learning by Predicting Noise
Bojanowski, P., & Joulin, A. (2017) · arXiv · doi:10.48550/arxiv.1704.05310 · Cited by 228
“In recent years, convolutional neural networks, or con-vnets (Fukushima, 1980; LeCun et al., 1989) have pushed the limits of computer vision (Krizhevsky et al., 2012; He et al., 2016), leading to important progress in a variety of tasks, like object detection (Girshick, 2015) or image segmentation…”
BackgroundHierarchical Neural Networks for Image Interpretation
Behnke, S. (2003) · Lecture Notes in Computer Science · doi:10.1007/b11963 · Cited by 225
Hyperspectral image classification via a random patches network
Xu, Y., Du, B., Zhang, F., & Zhang, L. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.05.014 · Cited by 223
Recurrent computations for visual pattern completion
Tang, H., Schrimpf, M., Lotter, W., Moerman, C., Paredes, A., Ortega Caro, J., Hardesty, W., Cox, D., & Kreiman, G. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1719397115 · Cited by 213
“models are characterized by hierarchical, feed-forward processing with progressive increases in the size of receptive fields, the degree of selectivity, and tolerance to object transformations (e.g. (4, 5, 27, 39)). Such models have been successfully used to describe rapid recognition of whole objects at the behaviora…”
Method70 years of machine learning in geoscience in review
Dramsch, J. S. (2020) · Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU) · Cited by 245
A hierarchical bayesian model of invariant pattern recognition in the visual cortex
George, D., & Hawkins, J. (2006) · Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. · doi:10.1109/ijcnn.2005.1556155 · Cited by 223
“the spatial information in images to achieve invariant representations[6][17][16].”
BackgroundHEp-2 Cell Image Classification With Deep Convolutional Neural Networks
Gao, Z., Wang, L., Zhou, L., & Zhang, J. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2526603 · Cited by 219
“A pioneering work of CNNs was Fukushima’s “neocognitron” [24].”
Encoding Multielement Scenes: Statistical Learning of Visual Feature Hierarchies.
Fiser, J., & Aslin, R. N. (2005) · Journal of Experimental Psychology: General · doi:10.1037/0096-3445.134.4.521 · Cited by 209
“Finally, a number of studies investigate more directly what the possible representations for object recognition are (Fukushima, 1980; Hummel & Biederman, 1992; Mel, 1997; Oram & Perrett, 1994; Riesenhuber & Poggio, 2000) and how to acquire them (Dayan et al., 1995; Poggio & Edelman, 1990; Wersing &…”
BackgroundTrainable ISTA for Sparse Signal Recovery
Ito, D., Takabe, S., & Wadayama, T. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2912879 · Cited by 223
“The recent advent of powerful neural networks (NNs) triggered the remarkable spread of research activities and applications on deep neural networks (DNNs) [20].”
BackgroundStar–galaxy classification using deep convolutional neural networks
Kim, E. J., & Brunner, R. J. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stw2672 · Cited by 221
A quantitative theory of immediate visual recognition
Serre, T., Kreiman, G., Kouh, M., Cadieu, C., Knoblich, U., & Poggio, T. (2007) · Progress in Brain Research · doi:10.1016/s0079-6123(06)65004-8 · Cited by 219
“The main contribution from this and other models of visual processing (Fukushima, 1980; Perrett and Oram, 1993; Mel, 1997; Wallis and Rolls, 1997; Riesenhuber and Poggio, 1999) has been to extend the notion of hierarchy beyond V1 to extrastriate areas and show how this can explain the tuning properties of neurons in h…”
BackgroundMethodInfluentialClassification of hyperspectral image based on deep belief networks
Li, T., Zhang, J., & Zhang, Y. (2014) · 2014 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2014.7026039 · Cited by 207
“Deep Learning Neural Networks date back at least to the 1980 Neocognitron by Kunihiko Fukushima [5].”
BackgroundAccurate and fast URL phishing detector: A convolutional neural network approach
Wei, W., Ke, Q., Nowak, J., Korytkowski, M., Scherer, R., & Woźniak, M. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107275 · Cited by 210
Handwritten alphanumeric character recognition by the neocognitron
Fukushima, K., & Wake, N. (1991) · IEEE Transactions on Neural Networks · doi:10.1109/72.97912 · Cited by 217
Self-citationScott, G. J., Marcum, R. A., Davis, C. H., & Nivin, T. W. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2722988 · Cited by 214
Toward the third generation artificial intelligence
Zhang, B., Zhu, J., & Su, H. (2023) · Science China Information Sciences · doi:10.1007/s11432-021-3449-x · Cited by 217
“…[22]), algorithm improvement (e.g., regularization to prevent overfitting [23]), new forms of networks (e.g., convolution neural networks (CNN) by Fukushima (Japan) [24,25] in 1980, recurrent neural networks [26], long short-term memory neural networks [27], and deep belief nets (DBN) [28]).”
BackgroundAttentional Selection for Object Recognition — A Gentle Way
Walther, D., Itti, L., Riesenhuber, M., Poggio, T., & Koch, C. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-36181-2_47 · Cited by 218
“Recognition of Attended Objects The recognition component is based on our previously published hierarchical model for object recognition HMAX [10,11] that considers recognition as a feedforward process in the spirit of Fukushima’s Neocognitron [ 12 ].”
MethodAutonomous reinforcement learning on raw visual input data in a real world application
Lange, S., Riedmiller, M., & Voigtlander, A. (2012) · The 2012 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2012.6252823 · Cited by 202
“1) Structure: The neural encoder net is a multilayer perceptron with a special “sparse” wiring structure in the first layers, that is inspired by principles found in the structure of the vertebrate retina and has been widely adapted in the neural networks community [32], [33].”
BackgroundA Diagnostic Study of Explainability Techniques for Text Classification
Atanasova, P., Simonsen, J. G., Lioma, C., & Augenstein, I. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.263 · Cited by 177
Convolutional-network models to predict wall-bounded turbulence from wall quantities
Guastoni, L., Güemes, A., Ianiro, A., Discetti, S., Schlatter, P., Azizpour, H., & Vinuesa, R. (2021) · Journal of Fluid Mechanics · doi:10.1017/jfm.2021.812 · Cited by 209
“Convolutional neural networks (CNNs) have become increasingly popular during the last years due to the hierarchical structure of their input (Fukushima 1980, 1988; LeCun et al. 1989; Lecun et al. 1998).”
BackgroundSimultaneous Detection and Segmentation
Hariharan, B., Arbeláez, P., Girshick, R., & Malik, J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.1808 · Cited by 161
“CNNs have their roots in the Neocogni-tron proposed by Fukushima [15].”
BackgroundMulti-Column Deep Neural Networks for offline handwritten Chinese character classification
Ciresan, D., & Meier, U. (2015) · 2015 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2015.7280516 · Cited by 203
“Weight-sharing convolutional neural networks (CNN) were introduced in 1979 [1], [2] as a simplified model of the mam malian visual cortex.”
MethodSeeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels
Misra, I., Zitnick, C. L., Mitchell, M., & Girshick, R. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.320 · Cited by 199
“, we use a vanilla classification model akin to Figure 2, in which an ImageNet [43] pre-trained ConvNet is fine-tuned to directly predict human-centric labels.”
MethodInfluentialDeep Learning Object Detection Methods for Ecological Camera Trap Data
Schneider, S., Taylor, G. W., & Kremer, S. (2018) · 2018 15th Conference on Computer and Robot Vision (CRV) · doi:10.1109/crv.2018.00052 · Cited by 184
Evaluation of Deep Learning Techniques in Sentiment Analysis from Twitter Data
Goularas, D., & Kamis, S. (2019) · 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML) · doi:10.1109/deep-ml.2019.00011 · Cited by 196
“Among them, convolutional neural networks [2],[3] and recurrent neural networks [4] were widely implemented because CNN respond very well to the dimensionality reduction problem and a category of RNN the LSTM networks [5] handle with success temporal or sequential data.”
MethodRecurrent Processing during Object Recognition
O’Reilly, R. C., Wyatte, D., Herd, S., Mingus, B., & Jilk, D. J. (2013) · Frontiers in Psychology · doi:10.3389/fpsyg.2013.00124 · Cited by 184
“…version of the ventral pathway have explained many aspects of the initial neural response properties across these different brain areas (Fukushima, 1980, 2003; Wal-lis O’Reilly et al. feedforward-driven neural responses theventralpathwayare sufficient tosolvereasonablychallenging…”
BackgroundZhao, B., Ding, R., Chen, S., Linares-Barranco, B., & Tang, H. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2362542 · Cited by 216
“However, most existing algorithms are based on conventional frame-driven image sensors.”
BackgroundDeep Networks with Internal Selective Attention through Feedback Connections
Stollenga, M., Masci, J., Gomez, F. J., & Schmidhuber, J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.3068 · Cited by 112
A survey of computer-aided diagnosis of lung nodules from CT scans using deep learning
Gu, Y., Chi, J., Liu, J., Yang, L., Zhang, B., Yu, D., Zhao, Y., & Lu, X. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104806 · Cited by 199
Plant phenomics: an overview of image acquisition technologies and image data analysis algorithms
Perez-Sanz, F., Navarro, P. J., & Egea-Cortines, M. (2017) · GigaScience · doi:10.1093/gigascience/gix092 · Cited by 197
“These multi-layered networks are formed by a layer of neurons that work in a convolutional way, reducing the sampling process to end with a layer of perception neurons for final classification [174].”
A neural network model for selective attention in visual pattern recognition
Fukushima, K. (1986) · Biological Cybernetics · doi:10.1007/bf00363973 · Cited by 208
“If we consider the afferent connections in the network only, and neglect the efferent ones, the model resembles the "neocognitron" which the author proposed earlier ( Fukushima 1980; Fukushima and Miyake 1982).”
BackgroundMethodResultSelf-citationValan, M., Makonyi, K., Maki, A., Vondráček, D., & Ronquist, F. (2019) · Systematic Biology · doi:10.1093/sysbio/syz014 · Cited by 194
“The basic ideas have been around for a long time (Fukushima 1979, 1980; Fukushima et al. 1983) but a significant increase in the complexity and size of the neural networks and a huge increase in the volume of data used for training have generated spectacular advances in recent years.”
BackgroundNahid, A.-A., Mehrabi, M. A., & Kong, Y. (2018) · BioMed Research International · doi:10.1155/2018/2362108 · Cited by 197
“[3] K. Fukushima, “Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position,” Biological Cybernetics, vol. 36, no. 4, pp. 193–202, 1980.”
BackgroundMethodInfluentialBeyond simple features: A large-scale feature search approach to unconstrained face recognition
Cox, D., & Pinto, N. (2011) · Face and Gesture 2011 · doi:10.1109/fg.2011.5771385 · Cited by 197
“Such efforts to model visual computations done by the brain have a long history, at least dating back to Fukushima’s Neocognitron (1980; [30]).”
BackgroundWhat and where: A Bayesian inference theory of attention
Chikkerur, S., Serre, T., Tan, C., & Poggio, T. (2010) · Vision Research · doi:10.1016/j.visres.2010.05.013 · Cited by 197
“…existing models of the ‘what’ pathway, such as hierarchical feedforward models of the ventral stream in the visual cortex (e.g., Amit & Mascaro, 2003; Fukushima, 1980; Mel, 1997; Riesenhuber & Poggio, 1999b; Serre, Kouh, et al., 2005; Thorpe, 2002; Ullman, Vidal-Naquet, & Sali, 2002; Wallis &…”
Using artificial neural networks to ask ‘why’ questions of minds and brains
Kanwisher, N., Khosla, M., & Dobs, K. (2023) · Trends in Neurosciences · doi:10.1016/j.tins.2022.12.008 · Cited by 182
“In the fi eld of computational vision, hand-engineered models of visual object recognition have been proposed for decades, but their performance lagged behind human abilities [8 – 10].”
BackgroundAdvances in AI and machine learning for predictive medicine
Sharma, A., Lysenko, A., Jia, S., Boroevich, K. A., & Tsunoda, T. (2024) · Journal of Human Genetics · doi:10.1038/s10038-024-01231-y · Cited by 177
“Here we focus more on biologically inspired CNNs [27], which are one of the fundamental architectures widely used in the computer vision domain, and their adoption to it has led to unprecedented improvements in performance.”
BackgroundA survey of swarm and evolutionary computing approaches for deep learning
Darwish, A., Hassanien, A. E., & Das, S. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-019-09719-2 · Cited by 200
“(3) The cost of implementing the architecture: Features extraction can be done before-hand and then the appropriate algorithm can be implemented as in Galloway et al. (2016), Liu et al. (2015b), Junbo et al. (2015). The objective of this process is to reduce the required training time and computational power.”
BackgroundMethodInfluentialA massively parallel architecture for a self-organizing neural pattern recognition machine
Carpenter, G. A., & Grossberg, S. (1986) · Computer Vision, Graphics, and Image Processing · doi:10.1016/0734-189x(86)90094-0 · Cited by 195
Finding strong gravitational lenses in the Kilo Degree Survey with Convolutional Neural Networks
Petrillo, C. E., Tortora, C., Chatterjee, S., Vernardos, G., Koopmans, L. V. E., Verdoes Kleijn, G., Napolitano, N. R., Covone, G., Schneider, P., Grado, A., et al. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx2052 · Cited by 187
Review on deep learning techniques for marine object recognition: Architectures and algorithms
Wang, N., Wang, Y., & Er, M. J. (2022) · Control Engineering Practice · doi:10.1016/j.conengprac.2020.104458 · Cited by 193
Sorin, V., Barash, Y., Konen, E., & Klang, E. (2020) · Academic Radiology · doi:10.1016/j.acra.2019.12.024 · Cited by 195
Advancing Computational Toxicology by Interpretable Machine Learning
Jia, X., Wang, T., & Zhu, H. (2023) · Environmental Science & Technology · doi:10.1021/acs.est.3c00653 · Cited by 183
The Psychophysical Evidence for a Binding Problem in Human Vision
Wolfe, J. M., & Cave, K. R. (1999) · Neuron · doi:10.1016/s0896-6273(00)80818-1 · Cited by 193
A comparison between shallow and deep architecture classifiers on small dataset
Pasupa, K., & Sunhem, W. (2016) · 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE) · doi:10.1109/iciteed.2016.7863293 · Cited by 175
Are Cortical Models Really Bound by the “Binding Problem”?
Riesenhuber, M., & Poggio, T. (1999) · Neuron · doi:10.1016/s0896-6273(00)80824-7 · Cited by 191
FoR: A Dataset for Synthetic Speech Detection
Reimao, R., & Tzerpos, V. (2019) · 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD) · doi:10.1109/sped.2019.8906599 · Cited by 193
“When first published in the 80’s, the idea of Convolutional Neural Networks (CNNs) was a groundbreaking finding [9].”
BackgroundHigh temporal resolution decoding of object position and category
Carlson, T. A., Hogendoorn, H., Kanai, R., Mesik, J., & Turret, J. (2011) · Journal of Vision · doi:10.1167/11.10.9 · Cited by 185
A deep learning framework for identifying children with ADHD using an EEG-based brain network
Chen, H., Song, Y., & Li, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.04.058 · Cited by 189
An introduction to deep learning in medical physics: advantages, potential, and challenges
Shen, C., Nguyen, D., Zhou, Z., Jiang, S. B., Dong, B., & Jia, X. (2020) · Physics in Medicine & Biology · doi:10.1088/1361-6560/ab6f51 · Cited by 185
“…M anuscript A uthor M anuscript A uthor M anuscript A uthor M anuscript not limited to full connection (Ivakhnenko and Lapa, 1965), convolution (Fukushima, 1980; LeCun et al., 1990; LeCun and Bengio, 1995), max-pooling/up-sampling (Scherer et al., 2010; Ciresan et al., 2011), batch…”
BackgroundMedical Image Segmentation: A Comprehensive Review of Deep Learning-Based Methods
Gao, Y., Jiang, Y., Peng, Y., Yuan, F., Zhang, X., & Wang, J. (2025) · Tomography · doi:10.3390/tomography11050052 · Cited by 240
“Convolutional Neural Networks (CNNs), initially proposed by Fukushima et al. [23], are widely used deep learning models for processing grid-structured data, such as images. are widely used deep learning models for processing grid-structured data, such as images As shown in Figure 3a, CNNs consist…”
Traven, H. G. C. (1991) · IEEE Transactions on Neural Networks · doi:10.1109/72.97913 · Cited by 192
CORnet: Modeling the Neural Mechanisms of Core Object Recognition
Kubilius, J., Schrimpf, M., Nayebi, A., Bear, D., Yamins, D. L. K., & DiCarlo, J. J. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/408385 · Cited by 177
Deep Learning Techniques for Future Intelligent Cross-Media Retrieval
Rehman, S. U., Waqas, M. M., Tu, S., Koubâa, A., Rehman, O. U., Ahmad, J. E., Hanif, M. I., & Han, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.01191 · Cited by 190
“Moving forward in 1980, Kunihiko Fukushima introduced Neocognitron in computer vision domain [58].”
BackgroundEarly History of Machine Learning
Fradkov, A. L. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.1888 · Cited by 190
“In 1980 Kunihiko Fukushima proposed a hierarchical multi-layered convolutional neural network, known as neocog-nitron Fukushima (1980).”
BackgroundWhen and Why Are Deep Networks Better Than Shallow Ones?
Mhaskar, H., Liao, Q., & Poggio, T. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10913 · Cited by 168
“The Neocognitron (Fukushima 1980) was a convolutional neural network that was trained to recognize characters.”
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.