Cited by 661Visual perception and processing mechanismsNeural Networks and ApplicationsAdvanced Image and Video Retrieval Techniques

The DOI matches its Crossref record; 14 of the 15 references it cites were found in a registry or an index.

Learning Invariance from Transformation Sequences

Földiák, Peter·1991·Neural Computation

DOI 10.1162/neco.1991.3.2.194

Open this paper in CoChat — free account

Abstract

The visual system can reliably identify objects even when the retinal image is transformed considerably by commonly occurring changes in the environment. A local learning rule is proposed, which allows a network to learn to generalize across such transformations. During the learning phase, the network is exposed to temporal sequences of patterns undergoing the transformation. An application of the algorithm is presented in which the network learns invariance to shift in retinal position. Such a principle may be involved in the development of the characteristic shift invariance property of complex cells in the primary visual cortex, and also in the development of more complicated invariance properties of neurons in higher visual areas.

Integrity signals

Registry

Crossref · 10.1162/neco.1991.3.2.194

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

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
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891
Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
Fukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759
Toward a modern theory of adaptive networks: Expectation and prediction.
Sutton, R. S., & Barto, A. G. (1981) · Psychological Review · doi:10.1037/0033-295x.88.2.135 · Cited by 1,450
Feature Discovery by Competitive Learning*
Rumelhart, D. E., & Zipser, D. (1985) · Cognitive Science · doi:10.1207/s15516709cog0901_5 · Cited by 1,398
Visual neurones responsive to faces in the monkey temporal cortex
Perrett, D. I., Rolls, E. T., & Caan, W. (1982) · Experimental Brain Research · doi:10.1007/bf00239352 · Cited by 1,385
Forming sparse representations by local anti-Hebbian learning
Földiák, P. (1990) · Biological Cybernetics · doi:10.1007/bf02331346 · Cited by 541
Adaptation and decorrelation in the cortex
Barlow, H. B., & Földiák, P. (1989) · Addison-Wesley Longman Publishing Co., Inc. eBooks · Cited by 263
Learning translation invariant recognition in a massively parallel networks
Hinton, G. E. (1987) · Lecture notes in computer science · doi:10.1007/3-540-17943-7_117 · Cited by 179
A complex-cell receptive-field model
Spitzer, H., & Hochstein, S. (1985) · Journal of Neurophysiology · doi:10.1152/jn.1985.53.5.1266 · Cited by 144

Show all 15 references

Research works printed but not linked: 2

Barlow H. B., 1989, Chap., 4, 54
Sutton R. S., 1981, Psychol. RKV., 88, 135

Sorted by citations

Items 501–600 of 660

On theorists and data in computational neuroscience
Hopfield, J. J. (2000) · Nature Neuroscience · doi:10.1038/81484 · Cited by 3
Sufficient encoding of dynamical systems
Creutzig, F. (2008) · edoc Publication server (Humboldt University of Berlin) · doi:10.18452/15817 · Cited by 3
A two-layer temporal generative model of natural video exhibits complex-cell-like pooling of simple cell outputs
Hurri, J., & Hyvärinen, A. (2003) · Neurocomputing · doi:10.1016/s0925-2312(02)00783-x · Cited by 3
Modelling the Development of the Retinogeniculate Pathway
Eglen, S. J., Barreau, P. G., Cox, C., JONES, P. M., Noble, J., & Parsowith, S. (1997) · OpenGrey (Institut de l'Information Scientifique et Technique) · Cited by 3
Localized learning in insects
Collett, T. S. (1993) · Nature · doi:10.1038/365693a0 · Cited by 3
Biologically Inspired Object Categorization in Cluttered Scenes
Peerasathein, T., Woo, M., & Gaborski, R. S. (2007) · Proceedings · doi:10.1109/aipr.2007.13 · Cited by 3
“The FENN is trained using the trace Hebbian learning rule [4, 5 ,6].”
Method
A survey of recent developments in theoretical neuroscience and machine vision
Colombe, J. B. (2004) · Proceedings · doi:10.1109/aipr.2003.1284273 · Cited by 3
“, the Cartesian coordinate space of pixel intensities) from one moment to the next [4-6].”
BackgroundMethod
Subjective physicsPreprint
Brette, R. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1311.3129 · Cited by 6
A biologically plausible neural network for Slow Feature AnalysisPreprint
Lipshutz, D., Windolf, C., Golkar, S., & Chklovskii, D. (2020) · Neural Information Processing Systems · doi:10.48550/arxiv.2010.12644 · Cited by 19
“However, there is no theoretical analysis of the algorithm in [8].”
Influential
Color and luminance processing in V1 complex cells and artificial neural networks
Bun, L. M., & Horwitz, G. D. (2023) · Color Research & Application · doi:10.1002/col.22903 · Cited by 2
Generic fitting models learn edge representations from prenatal retinal waves
Pandey, L., Wood, S. M. W., Cappell, B., & Wood, J. N. (2026) · Cognition · doi:10.1016/j.cognition.2025.106415 · Cited by 2
Invariant visual object and face learning in the ventral cortical visual pathway: A biologically plausible model
Zhang, C., Du, J., & Feng, J. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013959 · Cited by 2
The geometry of neural representation: From neural tuning to manifold geometry
Zhu, J., Zhu, M., Wu, P., He, Q. L., Wang, J., Niu, X., & Wang, Z. (2026) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2026.118193 · Cited by 3
Exploring a Mixed Representation for Encoding Temporal Coherence
Parkinson, J., Sandouk, U., & Chen, K. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46227-1_22 · Cited by 2
“By guiding representation learning from video towards the discovery of temporally coherent structure present in the raw image data, the capture of variance associated with the identity of individual objects is improved [2][3][4].”
Background
The effect of structure on image classification using signatures
Roccaforte, R., & Raudies, F. (2018) · Biological Cybernetics · doi:10.1007/s00422-018-0761-2 · Cited by 2
Object Recognition with Statistically Independent Features: A Model Inspired by the Primate Visual Cortex
Malmir, M., & Ghidary, S. S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-11876-0_18 · Cited by 2
“Földiák proposed the Trace learning rule to describe the mechanism in which invariant selectivity of neurons are developed from continuous spatial and temporal transformations of the objects [26].”
Background
The invariance hypothesis and the ventral stream
Leibo, J. Z. (2014) · Cited by 2
Learning Image Transformations without Training Examples
Pankov, S. V. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24031-7_17 · Cited by 2
“[5, 19, 21] transformation-invariant learning was achieved by incorporating delayed response to stimuli into Hebbian-like learning rules.”
BackgroundMethod
Relationship between an Input Sequence and Asymmetric Connections Formed by Theta Phase Precession and STDP
Sato, N., & Yamaguchi, Y. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02490-0_23 · Cited by 2
“The Modified Hebb rule for slow input components has been theoretically discussed in the visual [ 17 ] and reward-related systems [18].”
Background
Neurons That Confuse Mirror-Symmetric Object Views
Mutch, J., Leibo, J. Z., Smale, S., Rosasco, L., & Poggio, T. (2010) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 2
Combining Spatial Proximity and Temporal Continuity for Learning Invariant Representations
Kurşun, O., & Aytekin, T. (2012) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2012.157 · Cited by 2
Selective Attention in the Learning of Invariant Representation of Objects
Li, M., & Clark, J. J. (2006) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvpr.2005.522 · Cited by 2
“Finally we compare the performance of the proposed learning rule as in Equation 7 with the Hebbian trace rule ( [3]) and the temporal stability constraint rule (Equation 5).”
BackgroundMethodResultInfluential
Two sites of synaptic integration: relevant for learning?
Kording, K. P., & Peter König, B. (2000) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2000.860817 · Cited by 2
Action Recognition Using Hierarchical Independent Subspace Analysis with Trajectory
Luong, V. D., Wang, L., & Xiao, G. (2014) · Proceedings in adaptation, learning and optimization · doi:10.1007/978-3-319-13359-1_42 · Cited by 2
“3 to implement temporal slowness [32], [33], [34].”
Background
Towards a mesoscopic-level canonical circuit definition for visual cortical processing
Layher, G., Brosch, T., & Heiko Neumann, B. (2016) · International Conference on Bio-Inspired Models of Network, Information and Computing Systems (BIONETICS) · doi:10.4108/eai.3-12-2015.2262448 · Cited by 2
Self-organising coordinate transformation with peaked and monotonic gain modulation in the primate dorsal visual pathway
Navarro, D. D. M., Mender, B. M. W., Smithson, H. E., & Stringer, S. M. (2018) · PLoS ONE · doi:10.1371/journal.pone.0207961 · Cited by 2
Receptive Fields Similar to Simple Cells Maximize Temporal Coherence in Natural Video
Hurri, J., & Hyvärinen, A. (2002) · Lecture notes in computer science · doi:10.1007/3-540-46084-5_6 · Cited by 2
“The results also link the theory of achieving invariance by temporal coherence (F ¨ oldiák, 1991) to real-world visual data and measured properties of the visual system.”
BackgroundInfluential
Self-Organized Learning of 3 Dimensions
Szepesvári, C., & Lörincz, A. (1994) · Springer eBooks · doi:10.1007/978-1-4471-2097-1_70 · Cited by 2
Selection and Efficient Use of Local Features for Face and Facial Expression Recognition in a Cortical Architecture
Matsugu, M. (2007) · doi:10.5772/4843 · Cited by 2
Learning of Position-Invariant Object Representation Across Attention Shifts
Li, M., & Clark, J. J. (2005) · Lecture notes in computer science · doi:10.1007/978-3-540-30572-9_5 · Cited by 2
“Position invariance can be learned by imposing temporal continuity on the response of a network to temporal sequences of patterns undergoing transformation ([2], [4], [5], and [10]).”
Background
Unsupervised Learning of Temporal Constancies by Pyramidal-Type Neurons.
Eisele, M. (1997) · Operations research, computer science. Interface series · doi:10.1007/978-1-4615-6099-9_27 · Cited by 2
Combining DEKF algorithm and trace rule for fast on-line invariance extraction and recognition
Chang, S., Wong, K., & Leung, C.-S. (2000) · Pattern Recognition Letters · doi:10.1016/s0167-8655(00)00013-1 · Cited by 2
“With these goals, a signal mapping model was adopted by Foldiak (1991) and Wallis (1996, 1997) to learn the self-organizing invariant representation of input patterns by using the trace rule.”
BackgroundMethodInfluential
Learning Viewpoint Invariant Face Representations from Visual Experience by Temporal Association
Bartlett, M. S., & B, T. J. S. A. (1998) · Springer eBooks · doi:10.1007/978-3-642-72201-1_19 · Cited by 2
“This mechanism can learn transformation invariant representations when different views of an object are presented in temporal continuity (Foldiak, 1991; Weinshall, Edelman & Bulthoff, 1991; Rhodes, 1992; O'Reilly & Johnson, 1994).”
A simple probabilistic deep generative model for learning generalizable disentangled representations from grouped data.Preprint
Hosoya, H. (2018) · arXiv (Cornell University) · Cited by 2
Unsupervised changes in core object recognition behavior are predicted by neural plasticity in inferior temporal cortexPreprint
Jia, X., Hong, H., & DiCarlo, J. J. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.01.13.900837 · Cited by 2
Learning receptive field properties of complex cells in V1Preprint
Lian, Y., Almasi, A., Grayden, D. B., Kameneva, T., Burkitt, A. N., & Hamish Meffin, A. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.05.18.101873 · Cited by 2
The Role of Prototype Learning in Hierarchical Models of Vision
Thomure, M. D. (2000) · doi:10.15760/etd.1664 · Cited by 2
“The general problem of invariance learning has been considered in a handful of studies [47, 48, 49, 50, 51], and was applied to an HMAX-like system by Masquelier et al.”
Method
Learning Deep Visual Representations
Goh, H. (2013) · HAL · Cited by 2
Object Identification and Cortical Organization
Barlow, H. B. (1993) · Elsevier eBooks · doi:10.1016/b978-0-08-042004-2.50010-1 · Cited by 2
Extraction of visual features from natural video data using Slow Feature Analysis
Nickisch, H. (2006) · MPG.PuRe (Max Planck Society) · Cited by 2
Human Emotion Detection Using Deep Learning Neural Network
Rao, N., Tanveer, S., Khalid, S. S., & Alam, N. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-2535-1_42 · Cited by 1
Topographic Variational Autoencoders
Song, Y., Keller, T. A., Sebe, N., & Welling, M. (2025) · Synthesis lectures on computer vision · doi:10.1007/978-3-031-88111-4_3 · Cited by 1
On a model of visual cortex: learning invariance and selectivity
Caponnetto, A., Poggio, T., & Smale, S. (2008) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
Sensing with Artificial Tactile Sensors: An Investigation of Spatio-temporal Inference
Motiwala, A., Fox, C., Lepora, N. F., & Prescott, T. J. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23232-9_23 · Cited by 1
“Based on this property of temporal slowness, it has been suggested that the cortex learns to represent invariant and complex representations not just by matching spatial similarity of its inputs but by generalizing over successive spatial patterns in time [8,3].”
Background
STDP in lateral connections creates category-based perceptual cycles for invariance learning with multiple stimuli
Evans, B. D., & Stringer, S. M. (2014) · Biological Cybernetics · doi:10.1007/s00422-014-0637-z · Cited by 1
“Trace (Földiák 1991) and CT learning (Stringer et al. 2006) help to associate different images with temporal (Wallis and Rolls 1997; Li and DiCarlo 2008) and spatial overlap (Stringer et al. 2006), respectively, which are likely to represent the same objects.”
Background
Online learning of feature detectors from natural images with the probabilistic WKL rule
Léveillé, J., Hayashi, I., & Fukushima, K. (2012) · Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · doi:10.1109/scis-isis.2012.6505397 · Cited by 1
“One variation of Hebbian learning – the trace rule – uses low-pass filtered post-synaptic output with the hope of achieving spatial invariance through learning from continuously varying input [5, 14, 15].”
Background
Learning and disrupting invariance in visual recognition
Işık, L., Leibo, J. Z., & Poggio, T. (2011) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
Sequential Memory Retention by Stabilization of Cell Assemblies
Leleu, T. G., & Aihara, K. (2013) · Springer eBooks · doi:10.1007/978-94-007-4792-0_86 · Cited by 1
Multimap formation in visual cortex
Jain, R., Millin, R., & Mel, B. W. (2015) · Journal of Vision · doi:10.1167/15.16.3 · Cited by 1
Self-organization of V1 Complex Cells Based On Slow Feature Analysis And Retinal Waves
Wiskott, L. (2010) · Frontiers in Computational Neuroscience · doi:10.3389/conf.fncom.2010.51.00090 · Cited by 1
The visual development of hand-centered receptive fields in a neural network model of the primate visual system trained with experimentally recorded human gaze changes
Galeazzi, J. M., Navajas, J., Mender, B. M. W., Quiroga, R. Q., Minini, L., & Stringer, S. M. (2016) · Network Computation in Neural Systems · doi:10.1080/0954898x.2016.1187311 · Cited by 1
“Trace learning is a biologically plausible learning mechanism that encourages cells to learn to respond to input images that tend to occur in close temporal proximity (Földiák 1991).”
Background
Random Variable Transformations
Ogunnaike, B. A. (2009) · CRC Press eBooks · doi:10.1201/b17197-10 · Cited by 1
The Spiral Discovery Network as an Evolutionary Model for Gradient-Free Non-Convex Optimization
Csapó, Á. (2018) · IEEE International Conference on Cognitive Infocommunications · doi:10.1109/coginfocom.2018.8639877 · Cited by 1
“[10], [21], [25]).”
Object discrimination performance and dynamics evaluated by inferotemporal cell population activity
Wang, R. H., Dai, L., Okamura, J., Fuchida, T., & Wang, G. (2021) · IBRO Neuroscience Reports · doi:10.1016/j.ibneur.2021.02.008 · Cited by 1
Neuroscientific insights about computer vision models: a concise review
Susan, S. (2024) · Biological Cybernetics · doi:10.1007/s00422-024-00998-9 · Cited by 2
“Unsupervised Hebbian rules were put into use for biologically-inspired unsupervised learning way back in 1991 by Földiak and further explored in 1998 (Földiak 1991; Földiak 1998) Transformation-invariant representations of the object were derived by this form of unsupervised learning.”
Trace regulation techniques for feature extraction
Sha, L., Peng, H., & Sun, X. (2002) · International Conference on Signal Processing · doi:10.1109/icosp.1998.770838 · Cited by 1
Reverse engineering object recognition
Cox, D. (2007) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
How a Part of the Brain Might or Might Not Work: A New Hierarchical Model of Object Recognition
Riesenhuber, M. (2000) · Cited by 1
Neural mechanisms for face and orientation aftereffects
Zhao, C. X. (2011) · OpenGrey (Institut de l'Information Scientifique et Technique) · Cited by 1
Toward a Universal Cortical Algorithm: Examining Hierarchical Temporal Memory in Light of Frontal Cortical FunctionPreprint
Ferrier, M. R. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.4702 · Cited by 3
“In recent years several new approaches have made headway toward solving this problem, using the principle of temporal slowness (Berkes, 2005; Földiák, 1991; Mitchison, 1991).”
High-level visual object representations in inferior temporal cortex
Mur, M. (2011) · Research Publications (Maastricht University) · doi:10.26481/dis.20111202mm · Cited by 1
High-Level Visual Processing
Fukushima, T., Kasahara, H., Kamigaki, T., & Miyashita, Y. (2008) · Elsevier eBooks · doi:10.1016/b978-012370880-9.00289-9 · Cited by 1
Cortical Networks of Visual Recognition
Thériault, C., Thome, N., & Cord, M. (2015) · Wiley eBooks · doi:10.1002/9783527680863.ch13 · Cited by 1
A Model For Development of Cortical Lateral Connectivities Using Motion Information
Shams, L. B., & Fiser, J. (1998) · Springer eBooks · doi:10.1007/978-1-4615-4831-7_85 · Cited by 1
Learning of view-invariant pattern recognizer with temporal context
Inoue, K., & Urahama, K. (2000) · Pattern Recognition · doi:10.1016/s0031-3203(99)00146-6 · Cited by 1
“View-invariant pattern recognizers can be devised by unsupervised learning utilizing this temporal information [5].”
Background
Neural Clustering Of Correspondences For Visual Pose Estimation
Maul, T., & Baba, S. (2009) · European Conference on Modelling and Simulation (ECMS) · doi:10.7148/2009-0820-0826 · Cited by 1
“A modified Hebbian rule for example (Földiák 1991) might state that changes in synaptic strength are proportional to presynaptic activity and a temporal average of post-synaptic activity.”
Background
Using sparse trace neural network to extract temporal-spatial invariance
Peng, H., Gan, Q., Sha, L., & Yu, W. (2002) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1998.685961 · Cited by 1
Bayesian Modelling of Music: Algorithmic Advances and Experimental Studies of Shift-Invariant Sparse Coding
Blumensath, T. (2006) · ePrints Soton (University of Southampton) · Cited by 1
Convolutional Spiking Neural Network for Robust Object Detection with Population Code Using Structured Pulse Packets
Matsugu, M., Mori, K., & Mitarai, Y. (2004) · Studies in fuzziness and soft computing · doi:10.1007/978-3-540-39935-3_3 · Cited by 1
Solving the Binding Problem with Separated Extraction of Information by Oscillatory Self-Organizing Maps
Miyata, R., & Kurata, K. (2011) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2011.p1123 · Cited by 1
Neural network models
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0007 · Cited by 1
Visual attentional mechanisms
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0006 · Cited by 1
Complex Cells and the Representation of Local Image-Structure
Hansard, M. E., & Horaud, R. (2010) · Cited by 1
Learning mechanisms to account for the speed, selectivity and invariance of responses in the visual cortex
Masquelier, T. (2008) · Thèses en ligne de l'Université Toulouse III (Université Toulouse III) · Cited by 1
Gates for Handling Occlusion in Bayesian Models of Images: An Initial Study
Oberhoff, D., Endres, D., Giese, M. A., & Kolesnik, M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24455-1_21 · Cited by 1
“Both computer vision systems and models of (mammalian) biological vision have been researched extensively in the past few decades [4,5,9].”
Background
Learned Factorization Models to Explain Variability in Natural Image Sequences
Culpepper, B. J. (2011) · eScholarship (California Digital Library)
Integration of Artificial Neural Networks and Dynamic Concepts to an Adaptive and Self-Organizing Agent
Szepesvári, C., & Lörincz, A. (1993) · Springer eBooks · doi:10.1007/978-1-4471-2063-6_77
Neural Network Modelling of Hierarchical Motor Function in the Brain
Galeazzi, J. M., & Stringer, S. M. (2013) · Springer eBooks · doi:10.1007/978-3-642-39875-9_13
“In this case, how might a visual signal ei guide the development of the hand-centred response properties of these PPC cells during training in the light? Recently, Galeazzi et al. (2013) have proposed a biologically plausible model of how neurons in the PPC might develop their hand-centred responses to visual targets…”
Background
Learning Quadratic Forms by Density Estimation and its Applications to Image Coding
Bartsch, H., Hochreiter, S., & Obermayer, K. (2003)
An Anticipatory Self-Organized Map for Robust Recognition.
Swarup, S., Lakkaraju, K., Klementiev, A., Ray, S. R., & Sassen, E. (2005)
Dynamics of Neuronal Responses in the Inferotemporal Cortex Associated with 3D Object Recognition Learning
Yamaguchi, R., Honda, K., Okamura, J., Saruwatari, S., Oshima, J., & Wang, G. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-42051-1_25
“It has been proposed that different views of an object become associated when they are experienced in succession during rotation [1-2].”
Background
What happens next and when "next" happens: Mechanisms of spatial and temporal predictionPreprint
Wyatte, D. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.5328
“Information is relayed from the thalamus back up to layer 4 in a focal one-to-one manner that maintains microcolumnar separation (Sherman & Guillery, 2006; Thomson, 2010), which could allow temporal associations to be formed by local Hebbian learning mechanisms that track high probability co-occurences across past and…”
BackgroundInfluential
Stimulus evoked transient dynamics in the primary visual cortex in vivo : Voltage sensitive dye and extracellular recordings
Eriksson, D. (2008) · Figshare
A simple biologically inspired principal component analyzer-ModH neuron model
Jankovic, M. V. (2004) · Seminar on Neural Network Applications in Electrical Engineering (NEUREL) · doi:10.1109/neurel.2002.1057960
Handwritten digit recognition using trace neural network with EKF training algorithm
Wang, K., Sheng-Jiang, C., & Leung, C.-S. (2003) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs.1999.812281
Properties and processing of natural scenes
Kayser, C. (2004) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-004725724
An Adaptive Hierarchical Model of the Ventral Visual Pathway Implemented on a Mobile Robot
Bray, A. J. (2002) · Lecture notes in computer science · doi:10.1007/3-540-36181-2_55
“F¨ oldi´ ak initially used a trace rule [ 2 ] combined with local competition (as does [5]).”
BackgroundMethod
Selective Attention in the Learning of Viewpoint and Position Invariance
Li, M., & Clark, J. J. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-77343-6_17
“Feature maps are calculated by a set of “centresurround” operations, which are implemented as the difference between fine (at scale c ∈ [2, 3, 4]) and coarse scales (at scale s = c + δ ,w ithδ ∈ [3, 4 ]).”
MethodInfluential
Self-organization of complex-like cells
Fukushima, K., & Yoshimoto, K. (2003) · International Conference on Neural Information Processing · doi:10.1109/iconip.1999.843997
A learning rule for extracting temporal invariances
Stone, J. V., & Bray, A. J. (1995) · Lecture notes in computer science · doi:10.1007/3-540-59497-3_174
Learning mid-level motion features for the recognition of body movements
Sigala, R., Serre, T., Poggio, T., & Giese, M. A. (2010) · Journal of Vision · doi:10.1167/5.8.26
“The algorithm is based in a previous work of [3] who exploits a simple memory trace rule for the learning of shift invariance.”
Method
Unsupervised learning of spatial transformations in the absence of temporal continuity
Banerjee, B., & Dizaji, K. G. (2014) · IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP) · doi:10.1109/cimsivp.2014.7013276
“The pooling regions are often learned by exploiting temporal continuity (see for example, [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19]) which requires time-varying data.”
Neural network approach to the ECM problem
Gonoi, K., & Kurokawa, T. (2000) · Systems and Computers in Japan · doi:10.1002/1520-684x(200101)32:1
Glossing over too much
McCollum, G. (1997) · Behavioral and Brain Sciences · doi:10.1017/s0140525x97321608
Unsupervised learning algorithm for signal separation
Jacob, T., & Snyder, W. E. (2014) · IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP) · doi:10.1109/cimsivp.2014.7013286
“Oja’s rule models the relationship between different incoming weights to a single neuron, while SOM models the relationship between neurons themselves.”
Background
Development of invariant feature maps via a computational model of simple and complex cells
Huang, W., Ji, Z., Brumby, S. P., Kenyon, G. T., & Bettencourt, L. M. A. (2012) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2012.6252521
“(16) and (17), provide a trace-like rule for Hebbian learning, as is suggested in [5][14].”
BackgroundMethod
Learning invariant feature toward recognition modeling biology vision
Zou, Q., & Luo, S. (2005) · International Conference on Signal Processing · doi:10.1109/icosp.2004.1441634
“In neurobiology notion, nonlinearity between simple cells and cells in higher levels plays important role in transferring feature information([4]).”
Background
Cognitive Science and Psychology
Chow, S. L. (1994) · Journal of Intelligent Systems · doi:10.1515/jisys.1994.4.3-4.309
Biology vision inspired singularity model in invariant recognition
Zou, Q., & Luo, S. (2005) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2004.1380444
Development of shape primitives from images of composite objects represented by complex cells
Shams, L. B., & von der Malsburg, C. (1997) · Lecture notes in computer science · doi:10.1007/bfb0020266

Authors: Földiák, P.
Affiliations: Physiological Laboratory, University of Cambridge, Downing Street, Cambridge CB2 3EG, U.K.
Venue: Neural Computation
Publisher: MIT Press - Journals
Published: 1991-06
Volume: 3
Issue: 2
Pages: 194-200
ISSN: 0899-7667 (ISSN-L)
1530-888X
DOI: 10.1162/neco.1991.3.2.194
OpenAlex: W2096388912
Cited by: 661
References: 15
Citations by year: 2026: 9 · 2025: 6 · 2024: 10 · 2023: 12 · 2022: 11 · 2021: 20 · 2020: 16 · 2019: 18 · 2018: 21 · 2017: 16 · 2016: 37 · 2015: 20 · 2014: 31 · 2013: 24 · 2012: 28
FWCI: 5.77
Type: journal article
Language: en
Open access: closed
Locations: Neural Computation (publishedVersion)
PubMed (publishedVersion)
Topics: Life Sciences › Neuroscience › Cognitive Neuroscience › Visual perception and processing mechanisms
Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
Keywords: invariance learning, transformation sequences, translation invariance, local learning rules, visual object recognition, complex cells, primary visual cortex, visual system development

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

Learning Invariance from Transformation Sequences

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks