mlsanityData to 7 Oct 2026

Vector Symbolic Architectures as a Computing Framework for Emerging Hardware

arXiv 2106.05268 ↗First posted 9 Jun 2021cs.AR cs.AIcited by 35

Not on the map. Why?

Abstract (arXiv)

This article reviews recent progress in the development of the computing framework vector symbolic architectures (VSA) (also known as hyperdimensional computing). This framework is well suited for implementation in stochastic, emerging hardware, and it naturally expresses the types of cognitive operations required for artificial intelligence (AI). We demonstrate in this article that the field-like algebraic structure of VSA offers simple but powerful operations on high-dimensional vectors that can support all data structures and manipulations relevant to modern computing. In addition, we illustrate the distinguishing feature of VSA, "computing in superposition," which sets it apart from conventional computing. It also opens the door to efficient solutions to the difficult combinatorial search problems inherent in AI applications. We sketch ways of demonstrating that VSA are computationally universal. We see them acting as a framework for computing with distributed representations that can play a role of an abstraction layer for emerging computing hardware. This article serves as a reference for computer architects by illustrating the philosophy behind VSA, techniques of distributed computing with them, and their relevance to emerging computing hardware, such as neuromorphic computing.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 39 of its 213 references that are in the map. First posted on arXiv 9 Jun 2021.

Builds on

39 of 213 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  4. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  5. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  6. 2015Holographic Embeddings of Knowledge Graphscited by 181
  7. 2018All-Optical Machine Learning Using Diffractive Deep Neural Networkscited by 175
  8. 2018Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysiscited by 154
  9. 2019On the Turing Completeness of Modern Neural Network Architecturescited by 129
  10. 2019Superposition of many models into onecited by 64
  11. 2020A comparison of Vector Symbolic Architecturescited by 63
  12. 2020Classification using Hyperdimensional Computing: A Reviewcited by 60
27 more
  1. 2018Blessing of dimensionality: mathematical foundations of the statistical physics of datacited by 55
  2. 2019In-memory hyperdimensional computingcited by 47
  3. 2020A Theoretical Perspective on Hyperdimensional Computingcited by 43
  4. 2021Hyperdimensional computing as a framework for systematic aggregation of image descriptorscited by 32
  5. 2020Robust High-dimensional Memory-augmented Neural Networkscited by 31
  6. 2018A theory of sequence indexing and working memory in recurrent neural networkscited by 29
  7. 2020Variable Binding for Sparse Distributed Representations: Theory and Applicationscited by 27
  8. 2015Representing Objects, Relations, and Sequencescited by 24
  9. 2019Robust computation with rhythmic spike patternscited by 21
  10. 2019Rapid online learning and robust recall in a neuromorphic olfactory circuitcited by 17
  11. 2019Density Encoding Enables Resource-Efficient Randomly Connected Neural Networkscited by 15
  12. 2018Hardware Optimizations of Dense Binary Hyperdimensional Computing: Rematerialization of Hypervectors, Binarized Bundling, and Combinational Associative Memorycited by 14
  13. 2020End to End Binarized Neural Networks for Text Classificationcited by 13
  14. 2017Autoscaling Bloom Filter: Controlling Trade-off Between True and False Positivescited by 12
  15. 2017Neural Distributed Autoassociative Memories: A Surveycited by 12
  16. 2020Neuromorphic Nearest-Neighbor Search Using Intel's Pohoiki Springscited by 12
  17. 2017Integer Echo State Networks: Efficient Reservoir Computing for Digital Hardwarecited by 11
  18. 2018PULP-HD: Accelerating Brain-Inspired High-Dimensional Computing on a Parallel Ultra-Low Power Platformcited by 11
  19. 2019Recursive Sketches for Modular Deep Learningcited by 11
  20. 2020HyperEmbed: Tradeoffs Between Resources and Performance in NLP Tasks with Hyperdimensional Computing enabled Embedding of n-gram Statisticscited by 11
  21. 2020Commentaries on "Learning Sensorimotor Control with Neuromorphic Sensors: Toward Hyperdimensional Active Perception" [Science Robotics Vol. 4 Issue 30 (2019) 1-10cited by 7
  22. 2021Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networkscited by 7
  23. 2020Cellular Automata Can Reduce Memory Requirements of Collective-State Computingcited by 6
  24. 2021A 5 μ W Standard Cell Memory-based Configurable Hyperdimensional Computing Accelerator for Always-on Smart Sensingcited by 6
  25. 2018A Computational Theory for Life-Long Learning of Semanticscited by 5
  26. 2020On the computational power and complexity of Spiking Neural Networkscited by 3
  27. 2020Vector symbolic architectures for context-free grammarscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 1; 2023: 3; 2024: 12; 2025: 9; 2026: 7.

35 papers.

Sort:

By area:

  1. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challengescited by 68
  2. 2022Torchhd: An Open Source Python Library to Support Research on Hyperdimensional Computing and Vector Symbolic Architecturescited by 17
  3. 2023MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superpositioncited by 14
  4. 2021Hyperseed: Unsupervised Learning with Vector Symbolic Architecturescited by 8
  5. 2023Learning from Hypervectors: A Survey on Hypervector Encodingcited by 7
  6. 2023Computing with Residue Numbers in High-Dimensional Representationcited by 7
  7. 2024Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecturecited by 7
  8. 2024Generalized Holographic Reduced Representationscited by 6
  9. 2021Shift-Equivariant Similarity-Preserving Hypervector Representations of Sequencescited by 4
  10. 2024A Walsh Hadamard Derived Linear Vector Symbolic Architecturecited by 4
  11. 2025The Discovery Engine: A Framework for AI-Driven Synthesis and Navigation of Scientific Knowledge Landscapescited by 4
  12. 2024Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networkscited by 3
23 more
  1. 2024Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardwarecited by 3
  2. 2024Hyperdimensional computing: a fast, robust and interpretable paradigm for biological datacited by 2
  3. 2024H3DFact: Heterogeneous 3D Integrated CIM for Factorization with Holographic Perceptual Representationscited by 2
  4. 2024GPT-2 Through the Lens of Vector Symbolic Architecturescited by 2
  5. 2024Symbolic Disentangled Representations for Imagescited by 2
  6. 2025HyperCam: Low-Power Onboard Computer Vision for IoT Camerascited by 2
  7. 2025HD-CB: The First Exploration of Hyperdimensional Computing for Contextual Bandits Problemscited by 2
  8. 2025Linearithmic Clean-up for Vector-Symbolic Key-Value Memory with Kroneker Rotation Productscited by 2
  9. 2024Scheduled Knowledge Acquisition on Lightweight Vector Symbolic Architectures for Brain-Computer Interfacescited by 1
  10. 2025HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computingcited by 1
  11. 2025Vector Symbolic Algebras for the Abstraction and Reasoning Corpuscited by 1
  12. 2024Analogical Reasoning Within a Conceptual Hyperspacecited by 0
  13. 2024Improved Cleanup and Decoding of Fractional Power Encodingscited by 0
  14. 2025A Grid Cell-Inspired Structured Vector Algebra for Cognitive Mapscited by 0
  15. 2025Autonomous Learning with High-Dimensional Computing Architecture Similar to von Neumann'scited by 0
  16. 2025A Vector Symbolic Approach to Multiple Instance Learningcited by 0
  17. 2026ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decodingcited by 0
  18. 2026Contextual Bandits for Resource-Constrained Devices using Probabilistic Learningcited by 0
  19. 2026D2H-AD: A Hybrid Model Utilizing Hyperdimensional Computing for Advanced Anomaly Detectioncited by 0
  20. 2026Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphscited by 0
  21. 2026A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretabilitycited by 0
  22. 2026Superposed Latent Autoencodercited by 0
  23. 2026Superposed Inference for Hyperdimensional Computingcited by 0