Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Distributed representations were often criticized as inappropriate for encoding of data with a complex structure. However Plate's holographic reduced representations and Kanerva's binary spatter codes are recent schemes that allow on-the-fly encoding of nested compositional structures by real-valued or dense binary vectors of fixed dimensionality. In this article we consider procedures of the context-dependent thinning developed for representation of complex hierarchical items in the architecture of associative-projective neural networks. These procedures provide binding of items represented by sparse binary codevectors (with low probability of 1s). Such an encoding is biologically plausible and allows a high storage capacity of distributed associative memory where the codevectors may be stored. In contrast to known binding procedures, context-dependent thinning preserves the same low density (or sparseness) of the bound codevector for a varied number of component codevectors. Besides, a bound codevector is similar not only to another one with similar component codevectors (as in other schemes) but also to the component codevectors themselves. This allows the similarity of structures to be estimated by the overlap of their codevectors, without retrieval of the component codevectors. This also allows easy retrieval of the component codevectors. Examples of algorithmic and neural network implementations of the thinning procedures are considered. We also present representation examples for various types of nested structured data (propositions using role filler and predicate arguments schemes, trees, and directed acyclic graphs) using sparse codevectors of fixed dimension. Such representations may provide a fruitful alternative to the symbolic representations of traditional artificial intelligence as well as to the localist and microfeature-based connectionist representations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Marr, D. (1969) · The Journal of Physiology · doi:10.1113/jphysiol.1969.sp008820 · Cited by 3,253
Non-Holographic Associative Memory
WILLSHAW, D. J., BUNEMAN, O. P., & LONGUET-HIGGINS, H. C. (1969) · Nature · doi:10.1038/222960a0 · Cited by 979 · cited 2×
“Though the maximal storage capacity is reached at M=logN ( Willshaw, Buneman, & Longuet-Higgins, 1969; Palm, 1980), we use M≈√ N to get a network with a moderate number N of neurons and N2 connections at sufficient statistical stability of M (e.g.”
BackgroundMethodSmolensky, P. (1990) · Artificial Intelligence · doi:10.1016/0004-3702(90)90007-m · Cited by 959
Supervised neural networks for the classification of structures
Sperduti, A., & Starita, A. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.572108 · Cited by 666 · cited 1×
“Probably if additional multilayer perceptrons are introduced for each Context-Dependent Thinning 21 nesting level (with the input for each following perceptron provided by the hidden layer of the preceding one, similarly to Sperduti & Starita, 1997), generalization in those schemes would improve.”
BackgroundHolographic reduced representations
Plate, T. A. (1995) · IEEE Transactions on Neural Networks · doi:10.1109/72.377968 · Cited by 657 · cited 9×
“Let us note that angle brackets are used by Plate to denote normalization operation in HRRs (e.g. Plate, 1995; see also section 9.1.5).”
BackgroundMethodInfluential
Cited by
Kanerva, P. (2009) · Cognitive Computation · doi:10.1007/s12559-009-9009-8 · Cited by 970
Classification using hyperdimensional computing: a review
Ge, L., & Parhi, K. K. (2020) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2020.2988388 · Cited by 227
Hyper-Dimensional Computing Challenges and Opportunities for AI Applications
Hassan, E., Halawani, Y., Mohammad, B., & Saleh, H. (2022) · IEEE Access · doi:10.1109/access.2021.3059762 · Cited by 61
The problem of rapid variable creation
Hadley, R. F. (2009) · Neural Computation · doi:10.1162/neco.2008.07-07-572 · Cited by 23
Metadata
- Authors
- Rachkovskij, D. A., & Kussul, E. M.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2001-02
- Volume
- 13
- Issue
- 2
- Pages
- 411-452
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2167876429
- Cited by
- 119
- References
- 6
- FWCI
- 5.26
- 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: Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning. https://app.cochat.ai/papers/10.1162/089976601300014592
- The paper
- Rachkovskij, D. A., & Kussul, E. M. (2001). Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning. Neural Computation. https://doi.org/10.1162/089976601300014592
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.