The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Associative recall of memory without errors
Abstract
A neural network which is capable of recalling without errors any set of linearly independent patterns is studied. The network is based on a Hamiltonian version of the model of Personnaz et al. The energy of a state of N (\ifmmode\pm\else\textpm\fi{}1) neurons is the square of the Euclidean distance---in phase space---between the state and the linear subspace spanned by the patterns. This energy corresponds to nonlocal updatings of the synapses in the learning mode. Results of the mean-field theory (MFT) of the system as well as computer simulations are presented. The stable and metastable states of the network are studied as a function of ``temperature'' T and \ensuremath{\alpha}=p/N, where p is the number of embedded patterns. The maximum capacity of the network is \ensuremath{\alpha}=1. For all \ensuremath{\alpha} (0\ensuremath{\le}\ensuremath{\alpha}<1) the embedded patterns are not only locally stable but are global minima of the energy. The patterns appear, as metastable states, below a temperature T=${T}_{M}$(\ensuremath{\alpha}). The temperature ${T}_{M}$(\ensuremath{\alpha}) decreases to zero as \ensuremath{\alpha}\ensuremath{\rightarrow}1. The spurious states of the network are studied in detail in the case of random uncorrelated patterns. At finite p, they are identical to the mixture states of Hopfield's model. At finite \ensuremath{\alpha}, a spin-glass phase exists as a metastable state. According to the replica symmetric MFT the spin-glass state becomes degenerate with the patterns at \ensuremath{\alpha}=${\ensuremath{\alpha}}_{g}$=1-2/\ensuremath{\pi} and disappears above it. Possible interpretations of this unusual result are discussed. The average radius of attraction R of the patterns has been determined by computer simulations, for sizes up to N=400. The value of R for 0<\ensuremath{\alpha}<1 depends on the details of the dynamics. Results for both parallel and serial dynamics are presented. In both cases R is unity (the largest distance in phase space by definition) at \ensuremath{\alpha}\ensuremath{\rightarrow}0 and decreases monotonically to zero as \ensuremath{\alpha}\ensuremath{\rightarrow}1. Contrary to the MFT, simulations have not revealed, so far, any singularity in the properties of the spurious states at an intermediate value of \ensuremath{\alpha}.
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
“The approaches that have been explored lately also include systems for automatic analysis and synthesis of facial expressions [86], [56], [39], [47], [89], [88], [53], [14], [19]”
From Automatic analysis of facial expressions: the state of the art (2000) · cites this paper as [39]
Citations
Cites
Neural networks and physical systems with emergent collective computational abilities.
Hopfield, J. J. (1982) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.79.8.2554 · Cited by 19,270
Hopfield, J. J. (1984) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.81.10.3088 · Cited by 6,918
Solvable Model of a Spin-Glass
Sherrington, D., & Kirkpatrick, S. (1975) · Physical Review Letters · doi:10.1103/physrevlett.35.1792 · Cited by 3,577
Solution of 'Solvable model of a spin glass'
Thouless, D. J., Anderson, P. W., & Palmer, R. G. (1977) · Philosophical magazine · doi:10.1080/14786437708235992 · Cited by 1,305
Spin-glass models of neural networks
Amit, D. J., Gutfreund, H., & Sompolinsky, H. (1985) · Physical Review A · doi:10.1103/physreva.32.1007 · Cited by 1,201
Self-citationStoring Infinite Numbers of Patterns in a Spin-Glass Model of Neural Networks
Amit, D. J., Gutfreund, H., & Sompolinsky, H. (1985) · Physical Review Letters · doi:10.1103/physrevlett.55.1530 · Cited by 1,098
Self-citationOrder Parameter for Spin-Glasses
Parisi, G. (1983) · Physical Review Letters · doi:10.1103/physrevlett.50.1946 · Cited by 862
Information storage and retrieval in spin-glass like neural networks
Personnaz, L., Guyon, I., & Dreyfus, G. (1985) · Journal de Physique Lettres · doi:10.1051/jphyslet:01985004608035900 · Cited by 329
Collective properties of neural networks: A statistical physics approach
Peretto, P. (1984) · Biological Cybernetics · doi:10.1007/bf00317939 · Cited by 267
Neural networks with nonlinear synapses and a static noise
Sompolinsky, H. (1986) · Physical Review A · doi:10.1103/physreva.34.2571 · Cited by 230
Self-citation
Research works printed but not linked: 2
- 1986, Disordered Systems and Biological Organization
- A. E. Goles, 1986, Disordered Systems and Biological Organization
Cited by
Sorted by citations
Items 301–380 of 380
Interacting dreaming neural networks
Zanin, P., & Caticha, N. (2023) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/acc72b · Cited by 1
“It was shown that this increment occurs in part due to the fact that the synaptic matrix approaches the pseudo-inverse synaptic matrix [7], despite not converging to it.”
Critical dynamics and cyclic memory retrieval in non-reciprocal Hopfield networks
Xue, S., Maghrebi, M. F., Mias, G. I., & Piermarocchi, C. (2025) · SciPost Physics · doi:10.21468/scipostphys.19.4.100 · Cited by 2
“Since f ( t ) = const is an exact solution, the expansion only involves the time derivative, and we obtain Also, we note that The same prefactor, which we denote by θ 1 ( t ) , appears in both equations above.”
Robustness and information capacity of learning rules for neutral network models
Schnelle, T., & Engel, A. (1991) · Physics Letters A · doi:10.1016/0375-9601(91)90128-u · Cited by 1
Network Models of Neural Information Processing
Liang, P., Wu, S., & Gu, F. (2015) · Springer eBooks · doi:10.1007/978-94-017-7393-5_6 · Cited by 1
Writing to the Hopfield Memory via Training a Recurrent Network
Bao, H., Zhang, R., Mao, Y., & Huai, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29911-8_19 · Cited by 2
Phase diagrams for locally Hopfield neural networks in presence of correlated patterns
Piȩkniewski, F., & Schreiber, T. (2006) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2005.1555950 · Cited by 1
Loading Temporal Associative Memory Using the Neuronic Equation
Liou, C., & Sou, U.-C. (2003) · Lecture notes in computer science · doi:10.1007/3-540-44989-2_7 · Cited by 1
“…−1 −1 −1 −1 . . . ξ1. . . ξ2 . . . ξ3, and Φ3 = µ 1√ 2 ¶3 1 1 1 1 1 1 1 1 1 −1 1 −1 1 −1 1 −1 1 1 −1 −1 1 1 −1 −1 1 −1 −1 1 1 −1 −1 1 1 1 1 1 −1 −1 −1 −1 1 −1 1 −1 −1 1 −1 1 1 1 −1 −1 −1 −1 1 1 1 −1 −1 1 −1 1 1 −1 . . . 1 . . . ξ1 . . . ξ2 . . . ξ1ξ2 . . . ξ3 . . . ξ1ξ3 . . . ξ2ξ3 . . . ξ1ξ2ξ3 .”
Role of Self-Coupling in Dynamics of Diluted Hopfield Neural Networks
Bei-Lai, H., & Zhang, Y. (1996) · Chinese Physics Letters · doi:10.1088/0256-307x/13/1/001 · Cited by 1
Neural implementation of a method for solving systems of linear equations
Forbes, A., & Mansfield, A. (1990) · Network Computation in Neural Systems · doi:10.1088/0954-898x/1/2/006 · Cited by 1
Strongly diluted networks with selfinteraction
Englisch, H., Xiao, Y., & Yao, K. L. (1993) · Neural Networks · doi:10.1016/s0893-6080(05)80112-1 · Cited by 1
Maximum overlap neural networks for associative memory
Elizalde, E., Gómez, S., & August Romeo, A. (1992) · Physics Letters A · doi:10.1016/0375-9601(92)90779-l · Cited by 1
Retrieval property of associative memory with negative resistance
Hayakawa, Y., Li, H., & Nakajima, K. (2006) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2005.1556022 · Cited by 1
“ofthebasin size on thenegative resistance region, we define thebasin size[ 6 ].”
BackgroundMethodInfluentialThe Connectionist Model QNET and its Combination with Genetic Algorithms.
LOOCKE, P. V. (1996) · Philosophica · doi:10.21825/philosophica.82343 · Cited by 1
Neural Networks and Statistical Mechanics
Toulouse, G. (1987) · Springer eBooks · doi:10.1007/978-1-4684-7476-3_38 · Cited by 1
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0007 · Cited by 1
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0006 · Cited by 1
Hierarchical Organization of Memory
Feigel’man, M. V., & Ioffe, L. B. (1995) · Physics of neural networks · doi:10.1007/978-3-642-79814-6_5 · Cited by 1
Functional Connectivity-based Attractor Dynamics in Rest, Task, and DiseasePreprint
Englert, R., Kincses, B., Kotikalapudi, R., Gallitto, G., Li, J., Hoffschlag, K., Woo, C., Wager, T. D., Timmann, D., Bingel, U., et al. (2025) · eLife · doi:10.7554/elife.98725.2 · Cited by 1
Restricted Boltzmann machines : from compositional representations to protein sequence analysis
Tubiana, J. (2018) · theses.fr (ABES) · doi:10.70675/a6d497cfz68a4z42a8za422zbbc81f218ea5 · Cited by 7
Visual Comparison of Information Storage in Various Neural Network Models
Aberger, C., Folk, R., Kürten, K. E., & Schweng, H. K. (1992) · Perspectives in neural computing · doi:10.1007/978-1-4471-2001-8_23 · Cited by 1
Geometrical Perspective on Hairy Memory
Liou, C. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87559-8_90
“This is very different from correlation matrix designs, such as the pseudo-inverse method [ 16 ].”
MethodEncoding resolution in Hopfield associative memory networks
Voitovetsky, I., & Guterman, H. (2002) · IEEE Convention of Electrical and Electronics Engineers in Israel · doi:10.1109/eeis.1995.514160
A Generalised Entropy Based Associative Model
Nakagawa, M. M. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-69158-7_21
“Therein one may see again the great advantage of the present model based on the entropy functional to be minimized beyond the conventional quadratic form [ 12 ,13] even for comparison with the conventional autoassociation model defined by eq.(11).”
BackgroundMethodRecalling properties of non-random patterns in neural networks A Monte-Carlo study
Miranda, L., & Riera, R. (1998) · Physica A Statistical Mechanics and its Applications · doi:10.1016/s0378-4371(97)00499-8
On systolic general system solution for optimal artificial neural network training
Margaritis, K. G., & Evans, D. J. (1994) · International Journal of Computer Mathematics · doi:10.1080/00207169408804336
Effects of features of gK+(A) on retrieval in auto-associative networks
Berner, J. E. (1991) · Network Computation in Neural Systems · doi:10.1088/0954-898x/2/4/003
Invariant perception for symmetry related patterns
Mas, J., & Ramos (1989) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1989.118563
Enhancing Retrieval in Neural Networks
Andrecut, M. (1998) · Modern Physics Letters B · doi:10.1142/s0217984998001487
Multiplicity of metastable retrieval phases in networks of multistate neurons
Bös, S., & Kühn, R. (1994) · Journal of Statistical Physics · doi:10.1007/bf02187073
Analytical expressions for neural interactions which improve upon the projector rule
Coolen, A. C. C. (1991) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/24/11/031
The Research of Memory Model Based on Granular Computing
Xu, W., Wang, E., Xue, Q., & Changwei, Z. (2012) · International Conference on Computer Application and System Modeling · doi:10.2991/iccasm.2012.41
Metastable states of an asymmetric spin-glass with one stored pattern
Geppert, U., Schreckenberg, M., & Zittartz, J. (1994) · The European Physical Journal B · doi:10.1007/bf01307670
Tolerance of Pattern Storage Network for Storage and Recalling of Compressed Image using SOM
Singh, M. P., & Dixit, R. S. (2013) · International Journal of Computer Applications · doi:10.5120/12234-8516
“02”
Würtz, D., & Hartung, G. (1989) · Computer Physics Communications · doi:10.1016/0010-4655(89)90017-9
A trade-off formula in designing asymmetric neural networks
Xiong, D., & Zhao, H. W. (2013) · Journal of Physics A Mathematical and Theoretical · doi:10.1088/1751-8113/46/43/435002
“…the eigenvalue spectrum, we assume that the designed synaptic coupling J i , j can be written as a symmetric part J si , j with a weighting factor κ plus an asymmetric part J ai , j , i.e., For J si , j , if p N , it can be obtained by the pseudoinverse (PI) rule [24, 25], reading as (cid:7) (cid”
BackgroundMesoscopic Approach to Locally Hopfield Neural Networks in Presence of Correlated Patterns
Piȩkniewski, F. (2006) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2006.247321
Mean-field theory of the three-level associative memory and its synthesis
Ott, P. (2002) · IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks · doi:10.1109/icnn.1995.488888
Unlearning dynamics in Hopfield neural network
Plakhov, A. Y. (1994) · Radiophysics and Quantum Electronics · doi:10.1007/bf01039610
nmonotonie Neural Excellent etrieval Cap abilities
Asai, T., Yokotsuka, H., & Fukai, T. (1996)
Analyse der Eigenschaften von assoziativen Speichern f¨ ur die
der Arbeit, A. (1998)
Um estudo comparativo em memorias associativas com enfase em memorias associativas morfologicas
Mesquita, M. E. R. D. V. (2005) · doi:10.47749/t/unicamp.2005.359357
Stability and Switchability in Recurrent Neural Networks
Perumal, S. (2008) · OhioLink ETD Center (Ohio Library and Information Network)
Domany, E., & Meir, R. (1995) · Physics of neural networks · doi:10.1007/978-3-642-79814-6_9
The relaxation method for learning in artificial neural networks
Oh, H. (1992) · Iowa State University Digital Repository (Iowa State University)
A Computational Approach to the Neuropsychology of Visual Attention
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0011
Models of invariant object recognition
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0008
The cortical neurodynamics of visual attention - a model
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0009
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0003
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0012
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0013
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0002
Visual search: Attentional neurodynamics at work
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0010
Inferior temporal cortical visual areas
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0005
Topology optimization in spatially distributed cellular neural network
Bhambhani, V. (2025) · Library, Museums and Press - UDSpace (University of Delaware) · doi:10.58088/w57g-zf82
Yang, J., Li-xin, H., & Can, W. (2016) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec.2016.7867185
“Equilibrium properties of fully connected networks have been discussed detailedly through mean field [2] and spin glass [3] theory.”
Non-random weight dilution in high performance associative memories
Turvey, S. P., Hunt, S. P., Davey, N., & Frank, R. (2002) · University of Hertfordshire Research Archive (University of Hertfordshire)
Kinzel, W., & Opper, M. (1995) · Physics of neural networks · doi:10.1007/978-3-642-79814-6_4
High Performance Associative Memories and Structured Weight Dilution
Turvey, S. P., Hunt, S. P., Davey, N., & Frank, R. (2004) · Springer eBooks · doi:10.1007/978-3-540-45240-9_4
“Proceedings of the National Academy of Sciences (USA), 79, 2554-2558 [11] Kanter, I.”
BackgroundMethodInfluentialSzu, H. H., Georgiou, G. M., Cader, M., Cios, K. J., Armstrong, W. W., Morton, H., Aleksander, I., Thomas, M., Jutten, C., Almeida, L. B., et al. (1996) · Taylor & Francis eBooks · doi:10.1201/9781420050646.ptc
Torres‐Moreno, J. (2014) · Wiley eBooks · doi:10.1002/9781119004752.biblio
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0001
(2017) · Elsevier eBooks · doi:10.1016/b978-0-12-801895-8.00038-5
A Chaos Auto-Associative Model with Chebyshev Activation Function
Nakagawa, M. M. (2022) · IntechOpen eBooks · doi:10.5772/intechopen.106147
A Model For Hierarchical Memory Storage in Piriform CortexPreprint
Kumar, A. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.10.27.514001
“[16, 17].”
Introduction to linear algebra for neural networks
(2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.005.0001
(2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.002.0004
(2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.005.0002
(2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.002.0003
Análise de redes neurais de atratores interagentes por meio de um modelo com solução analítica
Zanin, P. (2022) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.43.2022.tde-22022023-134919
Hebbian Dreaming for Small DatasetsPreprint
Aquaro, M., Alemanno, F., Kanter, I., Durante, F., Adriano Barra, A., & Agliari, E. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4520891
Self-citationSpin-based modelling of perception as emergent from contextualized internal evaluation
Fanfarillo, L., Diez, G., Mayordomo, V. G., Bosch, M., Arias‐Gonzalez, J. R., & Valenzuela, B. (2026) · Royal Society Open Science · doi:10.1098/rsos.252221
Training oscillator Ising machines to assign the dynamic stability of their equilibrium points
Cheng, Y., & Lin, Z. (2026) · Physical review. E · doi:10.1103/h63g-kfnp
The Performance of Associative Memory Models with Biologically Inspired Connectivity
Chen, W. (2009) · University of Hertfordshire Research Archive (University of Hertfordshire)
Daydreaming algorithm for biased patterns
Doi, M., Ohzeki, M., & Ricci‐Tersenghi, F. (2026) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/ae8249 · Cited by 1
“A representative analytical approach is the pseudo-inverse rule [7,8].”
NLP models: Capacity per weight—capacity per label
Harel, Y., Halevi, T., Gross, R. D., Rosner, S., & Kanter, I. (2026) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2026.131855
Self-citationStatistical mechanics of neural networks and combinatorial optimization problems
Morabito, D. L. (1990) · RIT Scholar Works (Rochester Institute of Technology)
Connexionnisme, calcul, reconnaissance des formes et intelligence artificielle
Collobert, D., & Maruani, A. D. (1989) · Annals of Telecommunications · doi:10.1007/bf02995678
Metadata
- Authors
- Kanter, I., & Sompolinsky, H.
- Affiliations
- Bar-Ilan University (IL)
- Venue
- Physical Review A
- Publisher
- American Physical Society (APS)
- Published
- 1987-01-01
- Volume
- 35
- Issue
- 1
- Pages
- 380-392
- ISSN
- 0556-2791 (ISSN-L)
- OpenAlex
- W2029182425
- Cited by
- 379
- References
- 13
- Citations by year
- 2026: 9 · 2025: 11 · 2024: 13 · 2023: 6 · 2022: 10 · 2021: 9 · 2020: 6 · 2019: 6 · 2018: 1 · 2017: 4 · 2016: 4 · 2015: 2 · 2014: 7 · 2013: 6 · 2012: 6
- FWCI
- 30.30
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Physical Review A (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Physics and Astronomy › Condensed Matter Physics › Theoretical and Computational Physics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
- Keywords
- associative memory, mean-field theory, metastable states, spin glass phase, spurious states, Hopfield neural network, capacity
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
