The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Information storage in neural networks with low levels of activity
Abstract
The Hopfield model of a neural network is extended to allow for the storage and retrieval of biased patterns, {${\ensuremath{\xi}}_{i}^{\ensuremath{\mu}}$}, where ${N}^{\mathrm{\ensuremath{-}}1}$${\mathcal{J}}_{i}^{N}$${\ensuremath{\xi}}_{i}^{\ensuremath{\mu}}$=a is arbitrary. Such patterns represent levels of activity (i.e., percentage of firing neurons) equal to (1/2)(1+a), -1<a<1. If the coupling constants (synaptic efficacies) are constructed as in the original Hopfield model, the system can retrieve at most a very small number of patterns (p1+${a}^{\mathrm{\ensuremath{-}}2}$). This is due to the finite correlations (overlaps) between the patterns. The model is modified by subtracting the bias a from each pattern as it enters into the couplings. This modification restores the ability of the model to store a macroscopic number of patterns. Yet spurious states are found to plague the dynamics. It is then argued that the dynamics of the network should be consistent with the levels of activity of the stored patterns. This is implemented by adding a global constraint, which restricts the configuration space to states whose mean activity is in the neighborhood of (1/2)(1+a). The consequences of the restricted dynamics are analyzed in the replica symmetric mean-field theory. The global constraint suppresses spurious states and leads to the unexpected result that the storage capacity is higher than that of the unbiased network, up to very high values of the bias (\ensuremath{\Vert}a\ensuremath{\Vert}\ensuremath{\simeq}0.99). However, the information content of such networks is shown to be a monotonically decreasing function of a.
Overview
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.
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
Hopfield, J. J. (1984) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.81.10.3088 · Cited by 6,918
Self-Organization and Associative Memory
Kohonen, T. (1988) · Springer Series in Information Sciences · doi:10.1007/978-3-662-00784-6 · Cited by 3,812
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 1,182
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 1,058
Self-citationThe existence of persistent states in the brain
Little, W. A. (1974) · Mathematical Biosciences · doi:10.1016/0025-5564(74)90031-5 · Cited by 657
‘Unlearning’ has a stabilizing effect in collective memories
Hopfield, J. J., Feinstein, D. I., & Palmer, R. G. (1983) · Nature · doi:10.1038/304158a0 · Cited by 422
Associative recall of memory without errors
Kanter, I., & Sompolinsky, H. (1987) · Physical Review A · doi:10.1103/physreva.35.380 · Cited by 379
Self-citationInformation 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 331
Analytic study of the memory storage capacity of a neural network
Little, W. A., & Shaw, G. L. (1978) · Mathematical Biosciences · doi:10.1016/0025-5564(78)90058-5 · Cited by 228
Research works printed but not linked: 1
- G. Weisbuch, 1985, J. Phys. (Paris) Lett., 46, L, 10.1051/jphyslet:019850046014062300 · doi:10.1051/jphyslet:019850046014062300
Cited by
Nonlinear neural networks: Principles, mechanisms, and architectures
Grossberg, S. (1988) · Neural Networks · doi:10.1016/0893-6080(88)90021-4 · Cited by 1,623
Hippocampal conjunctive encoding, storage, and recall: Avoiding a trade‐off
O'Reilly, R. C., & McClelland, J. L. (1994) · Hippocampus · doi:10.1002/hipo.450040605 · Cited by 914
A synaptic organizing principle for cortical neuronal groups
Perin, R., Berger, T. K., & Markram, H. (2011) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1016051108 · Cited by 718
The Enhanced Storage Capacity in Neural Networks with Low Activity Level
Tsodyks, M. V., & Feigel'man, M. V. (1988) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/6/2/002 · Cited by 439
What determines the capacity of autoassociative memories in the brain?
Treves, A., & Rolls, E. (1991) · Network: Computation in Neural Systems · doi:10.1088/0954-898x/2/4/004 · Cited by 357
Metadata
- Authors
- Amit, D. J., Gutfreund, H., & Sompolinsky, H.
- Venue
- Physical Review A
- Publisher
- American Physical Society (APS)
- Published
- 1987-03-01
- Volume
- 35
- Issue
- 5
- Pages
- 2293-2303
- ISSN
- 0556-2791 (ISSN-L)
- OpenAlex
- W1966240450
- Cited by
- 329
- References
- 15
- FWCI
- 29.93
- Type
- journal article
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Information storage in neural networks with low levels of activity. https://app.cochat.ai/papers/10.1103/physreva.35.2293
- The paper
- Amit, D. J., Gutfreund, H., & Sompolinsky, H. (1987). Information storage in neural networks with low levels of activity. Physical Review A. https://doi.org/10.1103/physreva.35.2293
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.