Cited by 380Neural Networks and ApplicationsTheoretical and Computational PhysicsNeural dynamics and brain function

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

Kanter, I., Sompolinsky, H.·1987·Physical Review A

Open this paper in CoChat — free account

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}.

Integrity signals

Registry

Crossref · 10.1103/physreva.35.380

Cites

13 of 13 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?

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
Neurons with graded response have collective computational properties like those of two-state neurons.
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-citation
Storing 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-citation
Order 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

Flagged first, then by citations

Show all 13 references

Research works printed but not linked: 2

1986, Disordered Systems and Biological Organization
A. E. Goles, 1986, Disordered Systems and Biological Organization

Sorted by citations

Items 101–200 of 380

Convergence time and finite size effects in neural networks
Kohring, G. A. (1990) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/23/11/047 · Cited by 23
Neural networks with many-neuron interactions
Kohring, G. A. (1990) · Journal de physique · doi:10.1051/jphys:01990005102014500 · Cited by 23
Onset of 'super retrieval phase' and enhancement of the storage capacity in neural networks of nonmonotonic neurons
Shiino, M., & Fukai, T. (1993) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/26/17/014 · Cited by 23
Collective Phenomena in Neural Networks
van Hemmen, J. L., & Kühn, R. (1991) · Physics of neural networks · doi:10.1007/978-3-642-97171-6_1 · Cited by 22
Universality of unlearning
Wimbauer, S., Klemmer, N., & van Hemmen, J. L. (1994) · Neural Networks · doi:10.1016/0893-6080(94)90020-5 · Cited by 21
Neural networks: A biased overview
Domany, E. (1988) · Journal of Statistical Physics · doi:10.1007/bf01014882 · Cited by 23
The parietal cortex
Rolls, E. T. (2001) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780198524885.003.0004 · Cited by 22
Adiabatic quantum optimization for associative memory recall
Seddiqi, H., & Humble, T. S. (2014) · Frontiers in Physics · doi:10.3389/fphy.2014.00079 · Cited by 21
“This rule has a theoretical capacity of n for linearly independent patterns and approximately n/2 for interfering memories [6, 23].”
Background
Cell cycle time series gene expression data encoded as cyclic attractors in Hopfield systems
Szedlak, A., Sims, S., Smith, N. H., Paternostro, G., & Piermarocchi, C. (2017) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1005849 · Cited by 20
“A great deal of analytical and numerical work has been 9 devoted to understanding the statistical properties of the Hopfield model, including its 10 storage capacity [14], correlated patterns [15], spurious attractors [16], asymmetric 11 connections [17], embedded cycles [18], and complex transition landscapes [19].”
Background
Thouless-Anderson-Palmer equations for neural networks
Shamir, M., & Sompolinsky, H. (2000) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.61.1839 · Cited by 19
Self-citation
Mean-field analysis of hierarchical associative networks with 'magnetisation'
Krogh, A., & Hertz, J. (1988) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/21/9/033 · Cited by 20
Linking neural manifolds to circuit structure in recurrent networks
Pezon, L., Schmutz, V., & Wulfram Gerstner, B. (2026) · Neuron · doi:10.1016/j.neuron.2025.12.047 · Cited by 23
The loss surfaces of neural networks with general activation functions
Baskerville, N. P., Keating, J. P., Mezzadri, F., & Najnudel, J. (2021) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/abfa1e · Cited by 17
“Relationships between simpler neural networks and spin glasses have been known since [KS87; Gar88; EV01] and, more generally, connections between spin glass theory and computer science were studied in [Nis01] in the context of signal processing (image reconstruction, error correcting codes).”
Background
Dense Hebbian neural networks: A replica symmetric picture of supervised learning
Agliari, E., Albanese, L., Alemanno, F., Alessandrelli, A., Adriano Barra, A., Giannotti, F., Lotito, D., & Pedreschi, D. (2023) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2023.129076 · Cited by 22
“…mechanical has played a pivotal role for describing and quantifying information processing by neural networks for shallow (see e.g. [4, 17, 31, 34, 43, 49, 53]), deep (see e.g., [2, 14, 20, 41, 54]) and dense (see e.g. [5, 10, 12, 22, 44, 46]) architectures; in particular, investigations on dense…”
Background
Dynamics of Learning
Kinzel, W., & Opper, M. (1991) · Physics of neural networks · doi:10.1007/978-3-642-97171-6_4 · Cited by 19
Enlarged basin of attraction in neural networks with persistent stimuli
Engel, A., Bouten, M. C., Komoda, A., & Serneels, R. (1990) · Physical Review A · doi:10.1103/physreva.42.4998 · Cited by 19
Neural networks with high-order connections
Arenzon, J. J., & de Almeida, R. M. C. (1993) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.48.4060 · Cited by 16
Neural network models
Forrest, B. M., Roweth, D., Stroud, N., Wallace, D. J., & Wilson, G. (1988) · Parallel Computing · doi:10.1016/0167-8191(88)90110-x · Cited by 18
Distribution of Internal Fields and Dynamics of Neural Networks
Henkel, R. D., & Opper, M. (1990) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/11/5/003 · Cited by 18
The capacity of the dense associative memory networks
Bao, H., Zhang, R., & Mao, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.058 · Cited by 19
A constrained-optimization approach to training neural networks for smooth function approximation and system identification
Muro, G. D., & Ferrari, S. (2008) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2008.4634124 · Cited by 17
“Considerable success has also been met in the field of self-organizing networks and associative memories (e.g., [9], [10], [11], [12], [13]).”
Background
Tuned geometries of hippocampal representations meet the demands of social memoryPreprint
Boyle, L. M., Posani, L., Irfan, S., Siegelbaum, S. A., & Fusi, S. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.01.24.477361 · Cited by 17
“For example for the pseudo-inverse approach [8, 9, 3] it is clear that the memory capacity scales linearly with the dimensionality of the input patterns, which in our case is L.”
Background
The capacity and attractor basins of associative memory models
Davey, N., & Hunt, S. P. (1999) · Lecture notes in computer science · doi:10.1007/bfb0098189 · Cited by 16
“Averaging m0 over different stored patterns yields R = 1− m0 As is pointed out in [Kanter and Sompolinsky, 1987], the initial states used in this calculation may overlap one of the other stored patterns more closely than ξ p and to compensate for this, the definition of R is modified to: R = 1− 1−…”
Background
Increasing Attraction of Pseudo-Inverse Autoassociative Networks
Gorodnichy, D. O., & Reznik, A. M. (1997) · Neural Processing Letters · doi:10.1023/a:1009614025059 · Cited by 16
“It is known that self-connections severely restrict the size of attraction basins of prototypes [ 5 ].”
Background
Iterated learning in a layered feed-forward neural network
Meir, R., & Domany, E. (1988) · Physical Review A · doi:10.1103/physreva.37.2660 · Cited by 16
On the dynamics of memorization processes
Peretto, P. (1988) · Neural Networks · doi:10.1016/0893-6080(88)90004-4 · Cited by 16
Efficient and optimal binary Hopfield associative memory storage using minimum probability flowPreprint
Hillar, C. J., Sohl‐Dickstein, J., & Koepsell, K. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1204.2916 · Cited by 24
“Our next result is that at least n patterns in an n-node Hopfield network can be stored by minimizing (4) (see also [15, 16]).”
Background
scTOP: physics-inspired order parameters for cellular identification and visualization
Yampolskaya, M., Herriges, M. J., Ikonomou, L., Kotton, D. N., & Mehta, P. (2023) · Development · doi:10.1242/dev.201873 · Cited by 15
New Insights on Learning Rules for Hopfield Networks: Memory and Objective Function Minimisation
Tolmachev, P., & Manton, J. H. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207405 · Cited by 16
“In this section, we address the following question: how self-connectivity affects learning performance? It has been debated whether self-coupling is beneficial for memory storage in [3] [13] [6], but, it seems, the issue is still not resolved.”
Background
Replica symmetry breaking in neural networks with modified pseudo-inverse interactions
Доценко, В. С., & Tirozzi, B. (1991) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/24/21/026 · Cited by 16
A new learning approach to enhance the storage capacity of the Hopfield model
Oh, H., & Kothari, S. C. (1991) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1991.170650 · Cited by 15
Storage Capacity of the Hopfield Network Associative Memory
Wu, Y., Hu, J., Wu, W., Zhou, Y. Z., & Du, K.-L. (2012) · International Conference on Intelligent Computation Technology and Automation · doi:10.1109/icicta.2012.89 · Cited by 14
A Simple Derivation of a Bound on the Perceptron Margin Using Singular Value Decomposition
Barak, O., & Rigotti, M. (2011) · Neural Computation · doi:10.1162/neco_a_00152 · Cited by 14
“Our analysis also provides a straightforward derivation of the pseudo-inverse solution to the perceptron (Personnaz, Guyon, & Dreyfus, 1985; Kanter & Sompolinsky, 1987), which provides a closed-form expression for the weights of the perceptron that converges to the optimal solution for large values…”
BackgroundMethod
Finite Memory Loading in Hairy Neurons
Liou, C., & Lin, S.-L. (2006) · Natural Computing · doi:10.1007/s11047-004-5490-x · Cited by 15
“Several advanced designs have achieved varying degrees of success (Gardner, 1987,1989; Kanter and Sompolinsky, 1987; Tao et al., 2001).”
Influential
Chaotic itinerancy in the oscillator neural network without Lyapunov functions
Uchiyama, S., & Fujisaka, H. (2004) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/1.1785612 · Cited by 14
Phase transitions of neural networks
Kinzel, W. (1998) · Philosophical Magazine B · doi:10.1080/13642819808205038 · Cited by 19
Partially annealed neural networks
Feldman, D. E., & Доценко, В. С. (1994) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/27/13/015 · Cited by 14
Mean Field Theory Neural Networks for Feature Recognition, Content Addressable Memory and Optimization
Peterson, C. (1991) · Connection Science · doi:10.1080/09540099108946571 · Cited by 14
Stability and convergence of analog neural networks with multiple-time-step parallel dynamics
Marcus, C. M., & Westervelt, R. M. (1990) · Physical Review A · doi:10.1103/physreva.42.2410 · Cited by 14
The properties of models of simple neural networks
Amit, D. J. (1987) · Lecture notes in physics · doi:10.1007/bfb0057530 · Cited by 14
How Category Structure Influences the Perception of Object Similarity: The Atypicality Bias
Tanaka, J. W., Kantner, J., & Bartlett, M. (2012) · Frontiers in Psychology · doi:10.3389/fpsyg.2012.00147 · Cited by 12
“, faces) as distinct patterns of sustained activity (Kanter and Sompolinsky, 1987).”
Background
General potential surfaces and neural networks
Dembo, A., & Zeitouni, O. (1988) · Physical Review A · doi:10.1103/physreva.37.2134 · Cited by 15
Parallel dynamics of the neural network with the pseudoinverse coupling matrix
Henkel, R. D., & Opper, M. (1991) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/24/9/026 · Cited by 13
Erratum to: Dynamics control of semantic processes in a hierarchical associative memory
Cartling, B. G. (1996) · Biological Cybernetics · doi:10.1007/bf00194931 · Cited by 13
“On the basis of an approach to improving the storage capacity of correlated patterns in abstract neural networks (Personnaz et al. 1985, 1986; Kanter and Sompolinsky 1987 ) several storage schemes for hierarchically correlated patterns have been proposed (Parga and Virasoro 1986; Feigelman and Ioffe 1987; Cortes et al…”
Background
An alternative model for neural networks
de Almeida, R. M. C., & Iglesias, J. R. (1990) · Physics Letters A · doi:10.1016/0375-9601(90)90972-q · Cited by 13
Hebbian dreaming for small datasets
Agliari, E., Alemanno, F., Aquaro, M., Adriano Barra, A., Durante, F., & Kanter, I. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106174 · Cited by 12
Self-citation
Paramagnetic unlearning in neural network models
Nokura, K. (1996) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.54.5571 · Cited by 11
Associative memories using complex-valued Hopfield networks based on spin-torque oscillator arrays
Prasad, N., Mukim, P., Madhavan, A., & Stiles, M. D. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac7d05 · Cited by 13
Spin glass, the travelling salesman problem, neural networks and all that
Venkataraman, G., & Athithan, G. (1991) · Pramana · doi:10.1007/bf02846491 · Cited by 14
Storage of hierarchically correlated patterns
Engel, A. (1990) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/23/12/034 · Cited by 12
Optimal learning rules for familiarity detection
Greve, A., Sterratt, D. C., Donaldson, D. I., Willshaw, D. J., & van Rossum, M. C. W. (2008) · Biological Cybernetics · doi:10.1007/s00422-008-0275-4 · Cited by 12
“For instance, the pseudo-inverseruleishasahighercapacity(1bitpersynapse), but it is neither linear, nor local ( Kanter and Sompolinsky 1987; Hertz et al. 1991).”
Background
A high storage capacity neural network content-addressable memory
Hartman, E. (1991) · Network Computation in Neural Systems · doi:10.1088/0954-898x/2/3/006 · Cited by 12
Neural networks: A local learning prescription for arbitrary correlated patterns
Blatt, M., & Vergini, E. (1991) · Physical Review Letters · doi:10.1103/physrevlett.66.1793 · Cited by 12
Complex temporal association in neural networks
Kühn, R., van Hemmen, J. L., & Riedel, U. (1989) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/22/15/026 · Cited by 12
Gaussian and Exponential Architectures in Small-World Associative Memories
Calcraft, L., Adams, R., & Davey, N. (2006) · University of Hertfordshire Research Archive (University of Hertfordshire) · Cited by 12
Convergence time in infinite-range neural networks with parallel dynamics at zero temperature
Kanter, I. (1989) · Physical Review A · doi:10.1103/physreva.40.2611 · Cited by 11
Self-citation
Storing cycles in Hopfield-type networks with pseudoinverse learning rule: Admissibility and network topology
Zhang, C., Dangelmayr, G., & Oprea, I. (2013) · Neural Networks · doi:10.1016/j.neunet.2013.06.008 · Cited by 12
“To avoid this problem, a pseudoinverse learning rule was introduced by Amari (Amari, 1977), and in the Hopfield framework by Personnaz et al. and Kanter et al. (Personnaz et al., 1986; Kanter & Sompolinsky, 1987).”
BackgroundMethod
An Improved Version of the Pseudo-Inverse Solution for Classification and Neural Networks
Réfrégier, P., & Vignolle, J.-M. (1989) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/10/4/018 · Cited by 11
Daydreaming Hopfield Networks and their surprising effectiveness on correlated data
Serricchio, L., Bocchi, D., Chilin, C., Marino, R., Negri, M., Cammarota, C., & Ricci‐Tersenghi, F. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107216 · Cited by 18
“This local rule converges to the pseudo inverse rule for a large number of iterations [19], which means that it has the same problem of vanishing basins of attraction.”
The modified unlearning procedure for enhancing storage capacity in Hopfield network
Plakhov, A. Y., & Semenov, S. A. (1992) · IEEE Symposium on Neuroinformatics and Neurocomputers · doi:10.1109/rnns.1992.268563 · Cited by 10
Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network
Kurikawa, T., Barak, O., & Kaneko, K. (2020) · Physical Review Research · doi:10.1103/physrevresearch.2.023307 · Cited by 10
Dynamics control of semantic processes in a hierarchical associative memory
Cartling, B. G. (1995) · Biological Cybernetics · doi:10.1007/bf00199138 · Cited by 10
“On the basis of an approach to improving the storage capacity of correlated patterns in abstract neural networks (Personnaz et al. 1985, 1986; Kanter and Sompolinsky 1987) several storage schemes for hierarchically correlated patterns have been proposed (Parga and Virasoro 1986; Feigelman and Ioffe 1987; Cortes et al.”
Background
Derivation of Hebb's rule
Heerema, M., & van Leeuwen, W. A. (1999) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/32/2/004 · Cited by 10
Bidirectional associative memory with several patterns
Humpert, B. (1990) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1990.137657 · Cited by 9
The optimal value of self-connection
Gorodnichy, D. O. (2003) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1999.831579 · Cited by 10
Associative memories with short-range, higher order couplings
Karlholm, J. (1993) · Neural Networks · doi:10.1016/0893-6080(93)90008-k · Cited by 10
Locally-Connected and Small-World Associative Memories in Large Networks
Calcraft, L., Adams, R., & Davey, N. (2006) · Cited by 10
The decimation scheme for symmetric matrix factorization
Camilli, F., & Mézard, M. (2024) · Journal of Physics A Mathematical and Theoretical · doi:10.1088/1751-8121/ad2299 · Cited by 11
“However, there are other convenient iterative ways of modifying the Hebbian matrix [61–64] that converge to the so called pseudo-inverse learning rule (or modifications of it) [65–67], which in turn is able to increase the storage capacity to α c = 1.”
Eigenvector dreaming
Benedetti, M., Carillo, L., Marinari, E., & Mézard, M. (2024) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/ad138e · Cited by 11
Long sequence Hopfield memory*
Chaudhry, H. T., Zavatone-Veth, J. A., Krotov, D., & Pehlevan, C. (2024) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/ad6427 · Cited by 15
“Drawing inspiration from the pseudoinverse learning rule introduced by Kanter and Sompolinsky [43] for the classic Hopfield network, we propose a generalized pseudoinverse (GPI) transition rule where the overlap matrix O µν is positive-semidefinite, so we can define its pseudoinverse O + by…”
BackgroundMethod
Improvement of the Hopfield Neural Network by MC-Adaptation Rule
Zhen, Z., & Zhao, H. W. (2006) · Chinese Physics Letters · doi:10.1088/0256-307x/23/6/013 · Cited by 9
A Spin Glass Model for the Loss Surfaces of Generative Adversarial Networks
Baskerville, N. P., Keating, J. P., Mezzadri, F., & Najnudel, J. (2022) · Journal of Statistical Physics · doi:10.1007/s10955-022-02875-w · Cited by 9
“All of this recent activity sits in the context of earlier work connecting spin-glass objects with simple neural networks [KS87; Gar88; EV01] and, more generally, with image reconstruction and other signal processing problems [Nis01].”
Auto-associative memory based on a new hybrid model of SFNN and GRNN: Performance comparison with NDRAM, ART2 and MLP
Davande, H., Amiri, M., Sadeghian, A., & Chartier, S. (2008) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2008.4634026 · Cited by 9
Dynamical Interference between the Attractors in a Neural Network
Kohring, G. A. (1989) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/8/7/020 · Cited by 9
External fields in attractor neural networks with different learning rules
Rau, A., Sherrington, D., & Wong, K. Y. M. (1991) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/24/1/037 · Cited by 9
Quaternion-valued recurrent projection neural networks on unit quaternions
Valle, M. E., & Lobo, R. A. (2020) · Theoretical Computer Science · doi:10.1016/j.tcs.2020.08.033 · Cited by 9
Particle track classification using quantum associative memory
Quiroz, G., Ice, L., Delgado, A., & Humble, T. S. (2021) · Nuclear Instruments and Methods in Physics Research Section A Accelerators Spectrometers Detectors and Associated Equipment · doi:10.1016/j.nima.2021.165557 · Cited by 9
“Projection rules are expected to be an improvement on Hebb’s rule because they are designed to decorrelate the pattern set and minimize interference as part of the construction of W [20, 21].”
Background
Storing, learning and retrieving biased patterns
Agliari, E., Leonelli, F. E., & Marullo, C. (2021) · Applied Mathematics and Computation · doi:10.1016/j.amc.2021.126716 · Cited by 8
A multineuron interaction model for neural networks
Arenzon, J. J., de Almeida, R. M. C., & Iglesias, J. R. (1992) · Journal of Statistical Physics · doi:10.1007/bf01053798 · Cited by 8
Programming based learning algorithms of neural networks with self-feedback connections
Zhang, B., Zhaog, L., & Wu, F. (1995) · IEEE Transactions on Neural Networks · doi:10.1109/72.377985 · Cited by 8
Hopfield model with self-coupling
Singh, M. P. (2001) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.64.051912 · Cited by 8
A comparative analysis of high performance associative memory models.
Davey, N., & Hunt, S. P. (2000) · University of Hertfordshire Research Archive (University of Hertfordshire) · Cited by 8
Training with Noise: Application to Word and Text Storage
Gardner, E., Stroud, N., & Wallace, D. J. (1989) · Springer eBooks · doi:10.1007/978-3-642-83740-1_27 · Cited by 8
Neuronal networks in the hippocampus involved in memory
Treves, A., & Rolls, E. T. (2008) · Springer eBooks · doi:10.1007/3540532676_42 · Cited by 7
Design of a chaotic neural network for training and retrieval of grayscale and binary patterns
Taherkhani, A., Seyyedsalehi, S. A., & Jafari‬, A. H. (2011) · Neurocomputing · doi:10.1016/j.neucom.2011.03.037 · Cited by 7
Pseudo-Orthogonalization of Memory Patterns for Associative Memory
Oku, M., Makino, T., & Aihara, K. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2268542 · Cited by 6
Modeling disease progression in Multiple Myeloma with Hopfield networks and single-cell RNA-seq
Domanskyi, S., Hakansson, A., Paternostro, G., & Piermarocchi, C. (2019) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8983325 · Cited by 7
“The point attractor coupling matrix J ij is given by where guarantees memory recovery without errors at T = 0 [21], [22].”
Background
Unlearning in the paramagnetic phase of neural network models
Nokura, K. (1996) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/29/14/013 · Cited by 7
PDE/Statistical Mechanics Duality: Relation Between Guerra’s Interpolated p-Spin Ferromagnets and the Burgers Hierarchy
Fachechi, A. (2021) · Journal of Statistical Physics · doi:10.1007/s10955-021-02747-9 · Cited by 6
Backbone Structure of Hairy Memory
Liou, C. (2006) · Lecture notes in computer science · doi:10.1007/11840817_72 · Cited by 7
“We also did experiments on the pseudo-inverse learning rule under the label ‘PsdoInv’ [17][ 8 ].”
Method
Static and dynamic attractors of autoassociative neural networks
Gorodnichy, D. O., & Reznik, A. M. (1997) · Lecture notes in computer science · doi:10.1007/3-540-63508-4_128 · Cited by 7
Using generalized principal component analysis to achieve associative memory in a Hopfield net
Coombes, S., & Taylor, J. G. (1994) · Network Computation in Neural Systems · doi:10.1088/0954-898x/5/1/005 · Cited by 7
High performance associative memory models and symmetric connections
Davey, N., Adams, R. G., & Hunt, S. P. (2000) · University of Hertfordshire Research Archive (University of Hertfordshire) · Cited by 7
Storage Capacity and Learning in Ising-Spin Neural Networks
Forrest, B. M., & Wallace, D. (1991) · Physics of neural networks · doi:10.1007/978-3-642-97171-6_3 · Cited by 7
On the mapping between Hopfield networks and Restricted Boltzmann MachinesPreprint
Smart, M., & Zilman, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.11744 · Cited by 8
“1 of Kanter & Sompolinsky (1987) predicts β m ≈ 1 .”
BackgroundMethodInfluential
Hypercubic structures in orthogonal Hopfield models
Horn, D., & Weyers, J. (1987) · Physical Review A · doi:10.1103/physreva.36.4968 · Cited by 7
Neural Networks With Asynchronous Control.
Stinson, M. C. (1988) · doi:10.31390/gradschool_disstheses.4602 · Cited by 6
Statistical Mechanics of Neural Networks
Kinzel, W. (1989) · Physica Scripta · doi:10.1088/0031-8949/1989/t25/025 · Cited by 6
Categorization in the pseudo-inverse neural network
Neto, C. R., & Fontanari, J. F. (1998) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/31/2/013 · Cited by 6
Retrieval via non-equilibrium states in neural networks
Fontanari, J. F., & Köberle, R. (1988) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/21/12/009 · Cited by 6

Authors: Kanter, I., & Sompolinsky, H.
Affiliations: Bar-Ilan University (IL)
ORCID: Kanter, I.
Sompolinsky, H.
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)
DOI: 10.1103/physreva.35.380
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
Licence: link.aps.org/licenses/aps-default-license (vor)
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

Associative recall of memory without errors

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