The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
On a Model of Associative Memory with Huge Storage Capacity
Open accessOverview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The cited source doesn’t support the claim as written.
In the citing paper
“Interaction functions of the form F ( x ) = exp( x ) lead to exponential storage capacity of 2 d/ 2 where all stored patterns are fixed points but the radius of attraction vanishes (Demircigil et al., 2017).”
From Hopfield Networks is All You Need (2020) · cites this paper as Demircigil et al., 2017
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Modern binary Hopfield networks with energy functions based on interaction functions of the form F ( x ) = exp( x ) even lead to storage capacity of 2 d/ 2 , where all stored binary patterns are fixed points but the radius of attraction vanishes (Demircigil et al., 2017).”
From Hopfield Networks is All You Need (2020) · cites this paper as Demircigil et al., 2017
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This energy leads to an exponential storage capacity of N = 2 d/ 2 for binary patterns.”
From Hopfield Networks is All You Need (2020) · cites this paper as Demircigil et al., 2017
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This model was generalized by Demircigil et al. (Demircigil et al., 2017) to exponential interaction functions F ( x ) = exp( x ) , which gives the energy E = -exp(lse(1 , X T ξ )) .”
From Hopfield Networks is All You Need (2020) · cites this paper as Demircigil et al., 2017
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Furthermore, with a single update the fixed point is recovered with high probability.”
From Hopfield Networks is All You Need (2020) · cites this paper as Demircigil et al., 2017
Experimental — accuracy not yet measured
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It has been shown that the network converges with high probability after one update (Demircigil et al., 2017).”
From Hopfield Networks is All You Need (2020) · cites this paper as Demircigil et al., 2017
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Interaction functions of the form F ( x ) = x n lead to storage capacity of α n d n -1 , where α n depends on the allowed error probability (Krotov & Hopfield, 2016; 2018; Demircigil et al., 2017) (see (Krotov & Hopfield, 2018) for the non-binary case).”
From Hopfield Networks is All You Need (2020) · cites this paper as Demircigil et al., 2017
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Theorem A10 (Storage Capacity for Binary Modern Hopfield Nets (Demircigil et al. 2017)) . Consider the generalized Hopfield model with the dynamics described in Eq. (545) and interaction function F given by F ( x ) = e x . For a fixed 0 < α < ln(2) / 2 let N = exp( αd ) + 1 and let x 1 , . . . , x N be N patterns chosen uniformly at random from {-1 , +1 } d .”
From Hopfield Networks is All You Need (2020) · cites this paper as Demircigil et al., 2017
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
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
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
Large Deviations Techniques and Applications
Dembo, A., & Zeitouni, O. (2009) · Applications of mathematics · doi:10.1007/978-3-642-03311-7 · Cited by 1,056
The capacity of the Hopfield associative memory
McEliece, R., Posner, E., Rodemich, E., & Venkatesh, S. (1987) · IEEE Transactions on Information Theory · doi:10.1109/tit.1987.1057328 · Cited by 910
Memory capacity in neural network models: Rigorous lower bounds
Newman, C. M. (1988) · Neural Networks · doi:10.1016/0893-6080(88)90028-7 · Cited by 121
Rigorous results for the Hopfield model with many patterns
Talagrand, M. (1998) · Probability Theory and Related Fields · doi:10.1007/s004400050148 · Cited by 88
On the storage capacity of Hopfield models with correlated patterns
Löwe, M. (1998) · The Annals of Applied Probability · doi:10.1214/aoap/1028903378 · Cited by 51
Self-citationThe spin-glass phase-transition in the Hopfield model with $p$-spin interactions
Bovier, A., & Niederhauser, B. M. (2001) · Advances in Theoretical and Mathematical Physics · doi:10.4310/atmp.2001.v5.n6.a2 · Cited by 28
Lower bounds on the restitution error in the Hopfield Model
Daria, L. (1997) · Probability Theory and Related Fields · doi:10.1007/s004400050081 · Cited by 23
Research works printed but not linked: 2
- Krotov, D., Hopfield, J.J.: Dense associative memory for pattern recognition. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29, pp. 1172–1180. Curran Associates, Inc., Red Hook (2016)
- Löwe, M.: The storage capacity of generalized Hopfield models with semantically correlated patterns. Markov Process. Relat. Fields 5(1), 1–19 (1999)
Cited by
Sorted by citations
Items 101–135 of 135
Estimate of the Storage Capacity of q-Correlated Patterns in Hopfield Neural Networks
Wedemann, R. S., Plastino, A. R., Tsallis, C., & Curado, E. M. F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72341-4_10
Self-attention as an attractor network: transient memories without backpropagation
D’Amico, F., & Negri, M. (2024) · Complexity in Engineering (COMPENG) · doi:10.1109/compeng60905.2024.10741429
The connections between physics and AI: A review of the 2024 Nobel Prize in Physics
Tang, Q.-Y. (2024) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/tb-2024-1156
Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks
Sargolzaei, S., & Rueda, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78395-1_6
Improving Recall in Sparse Associative Memories That Use Neurogenesis
Warr, K., Hare, J. S., & Thomas, D. (2025) · Neural Computation · doi:10.1162/neco_a_01732
Topological constraints on self-organization in locally interacting systems
Sacco, F. M., Sakthivadivel, D. A. R., & Levin, M. (2026) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2025.0011 · Cited by 1
Computational Models of Hippocampal Cognitive Function
Bush, D., & Burgess, N. (2025) · Oxford University Press eBooks · doi:10.1093/med/9780190065324.003.0016
Symmetry Breaking in Neural Network Optimization: Insights from Input Dimension ExpansionPreprint
Meng, D., Zhang, J., Cheng, N., Li, F., Wang, X., Chen, J., & Pang, L.-G. (2025) · Research Square · doi:10.21203/rs.3.rs-5768541/v1
Modern Hopfield-Heuristic Physical Computing Architecture for Diabetes Prediction
Wu, R., Jiang, G., & Liu, P. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11043603
Cancer Survival Prognosis From Whole Slide Images Using Hopfield Network
Zhang, B., Liu, L., & Hao, B. (2025) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea65460.2025.11102231
Modern Complex-Valued Hopfield Network for Associative Memory of Continuous and Periodic Patterns
Hashimoto, T., Isokawa, T., Kobayashi, M., & Kamiura, N. (2025) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2025map0008
Shaping Attractor Landscapes in Boolean Liquid State Machines via STDP and Global Plasticity
Cabessa, J., & Villa, A. E. P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04552-2_20 · Cited by 1
All-to-All Connected Oscillator Ising Machines and Their Application as Associative Memory
Cheng, Y., & Lin, Z. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3609571 · Cited by 2
Attractor Regimes of Boolean Recurrent Neural Networks subject to STDP and Global Plasticity
Cabessa, J., & Villa, A. E. P. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228685
Bauckhage, C., & Sifa, R. (2025) · Cognitive technologies · doi:10.1007/978-3-031-99402-9_6
A 63.3 μW Modern Hopfield Network Hardware Accelerator Enabling Dense Associative Memory
Töreyin, H. (2025) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas53549.2025.11244487
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
Optical Hopfield neural networks with enhanced storage capacity
Li, Z., Kumar, S., Katidis, M., Musa, K., Huang, Y., & Qu, C. (2026) · Optics Letters · doi:10.1364/ol.584466
A Journey into Higher-Order Interactions: A Tribute to Shun-ichi Amari, Kyoto Prize Laureate
Shimazaki, H. (2025) · The Brain & Neural Networks · doi:10.3902/jnns.32.189
Origin of non-zero overlap in Hopfield neural networks beyond storage capacity
Fang, F., Wang, S.-J., & Huang, Z. (2026) · Cognitive Neurodynamics · doi:10.1007/s11571-026-10413-7
Fast variable selection under $$\ell _0$$ regularization in high-dimensions
Xiao, Y., & Walker, S. G. (2026) · Statistics and Computing · doi:10.1007/s11222-026-10853-5
Inference acceleration and optimization in deep neural networks for computer vision
Keddous, F. E. (2022) · theses.fr (ABES) · doi:10.70675/b08b2f98z66c2z46d7za694z241b7296cbd2
Chalvidal, M. (2023) · theses.fr (ABES) · doi:10.70675/d35a8a98zd3cfz4df4za6e9zf26f90d6f965
Transient dynamics of associative memory models
Clark, D. G. (2026) · Physical review. E · doi:10.1103/42y2-bsh1 · Cited by 9
The dimensionality of the Hopfield model
Erazo, C., Acevedo, S., & Ingrosso, A. (2026) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2026.131609
Farooq, H. (2026) · Research Square · doi:10.21203/rs.3.rs-10013690/v1
Li, Y., & Aihara, K. (2026) · Frontiers in Network Physiology · doi:10.3389/fnetp.2026.1778380
Analysis of the Hopfield model incorporating the effects of unlearning
Takeuchi, S., Takahashi, T., & Kabashima, Y. (2026) · Journal of Physics A Mathematical and Theoretical · doi:10.1088/1751-8121/ae8f87 · Cited by 1
Self-attention in large language models as adaptive stochastic mixing
Oosawa, C. (2026) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2026.131824
Scaling Associative Memory: A Sparse Graph Approach Versus Modern Hopfield Networks
Starzyk, J. A., Raif, P., Stokłosa, P., Horzyk, A., & Bulanda, D. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3726352
From Concepts to Relations: Generative Models as Relational Associative Memories
Donghi, G., Lollato, F., Spinello, V., Sperduti, A., Alippi, C., & Navarin, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38398-3_15
On Associative Neural Networks for Sparse Patterns with Large Capacities
Löwe, M., & Vermet, F. (2026) · Journal of Statistical Physics · doi:10.1007/s10955-026-03713-z
Self-citationLarge Associative Memory Problem in Neurobiology and Machine Learning
Krotov, D., & Hopfield, J. (2020) · arXiv · doi:10.48550/arxiv.2008.06996 · Cited by 67
Associative Memories via Predictive Coding
Salvatori, T., Song, Y., Hong, Y., Frieder, S., Sha, L., Xu, Z., Bogacz, R., & Lukasiewicz, T. (2021) · arXiv · doi:10.48550/arxiv.2109.08063 · Cited by 33
Metadata
- Authors
- Demircigil, M., Heusel, J., Löwe, M., Upgang, S., & Vermet, F.
- Affiliations
- École Normale Supérieure - PSL (FR)
- University of Münster (DE)
- Centre National de la Recherche Scientifique (FR)
- Corresponding author
- Vermet, Franck
- Venue
- Journal of Statistical Physics
- Published
- 2017-05-19
- Volume
- 168
- Issue
- 2
- Pages
- 288-299
- ISSN
- 0022-4715 (ISSN-L)
- 1572-9613
- OpenAlex
- W2587333550
- Cited by
- 136
- References
- 13
- Citations by year
- 2026: 17 · 2025: 35 · 2024: 31 · 2023: 19 · 2022: 7 · 2021: 12 · 2020: 6 · 2019: 2 · 2018: 4 · 2017: 3
- FWCI
- 2.45
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Journal of Statistical Physics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
- Physical Sciences › Physics and Astronomy › Condensed Matter Physics › Theoretical and Computational Physics
- Keywords
- associative memory, Hopfield neural network, storage capacity, basins of attraction, artificial neural networks
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
