mlsanityData to 14 Oct 2026

Hyperseed: Unsupervised Learning with Vector Symbolic Architectures

arXiv 2110.08343 ↗First posted 15 Oct 2021cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Motivated by recent innovations in biologically-inspired neuromorphic hardware, this article presents a novel unsupervised machine learning algorithm named Hyperseed that draws on the principles of Vector Symbolic Architectures (VSA) for fast learning of a topology preserving feature map of unlabelled data. It relies on two major operations of VSA, binding and bundling. The algorithmic part of Hyperseed is expressed within Fourier Holographic Reduced Representations model, which is specifically suited for implementation on spiking neuromorphic hardware. The two primary contributions of the Hyperseed algorithm are, few-shot learning and a learning rule based on single vector operation. These properties are empirically evaluated on synthetic datasets as well as on illustrative benchmark use-cases, IRIS classification, and a language identification task using n-gram statistics. The results of these experiments confirm the capabilities of Hyperseed and its applications in neuromorphic hardware.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 25 of its 108 references that are in the map. First posted on arXiv 15 Oct 2021.

Builds on

25 of 108 references.

References · 25

  1. 2019Superposition of many models into onecited by 64
  2. 2018Blessing of dimensionality: mathematical foundations of the statistical physics of datacited by 55
  3. 2019In-memory hyperdimensional computingcited by 48
  4. 2021Computing on Functions Using Randomized Vector Representationscited by 41
  5. 2021Vector Symbolic Architectures as a Computing Framework for Emerging Hardwarecited by 35
  6. 2021Hyperdimensional computing as a framework for systematic aggregation of image descriptorscited by 32
  7. 2020Robust High-dimensional Memory-augmented Neural Networkscited by 31
  8. 2018A theory of sequence indexing and working memory in recurrent neural networkscited by 29
  9. 2020Variable Binding for Sparse Distributed Representations: Theory and Applicationscited by 27
  10. 2019Robust computation with rhythmic spike patternscited by 21
  11. 2019Density Encoding Enables Resource-Efficient Randomly Connected Neural Networkscited by 15
  12. 2020End to End Binarized Neural Networks for Text Classificationcited by 13
13 more
  1. 2017Autoscaling Bloom Filter: Controlling Trade-off Between True and False Positivescited by 12
  2. 2017Neural Distributed Autoassociative Memories: A Surveycited by 12
  3. 2020Neuromorphic Nearest-Neighbor Search Using Intel's Pohoiki Springscited by 12
  4. 2021Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computingcited by 12
  5. 2017Integer Echo State Networks: Efficient Reservoir Computing for Digital Hardwarecited by 11
  6. 2020HyperEmbed: Tradeoffs Between Resources and Performance in NLP Tasks with Hyperdimensional Computing enabled Embedding of n-gram Statisticscited by 11
  7. 2020Commentaries on "Learning Sensorimotor Control with Neuromorphic Sensors: Toward Hyperdimensional Active Perception" [Science Robotics Vol. 4 Issue 30 (2019) 1-10cited by 7
  8. 2020Prive-HD: Privacy-Preserved Hyperdimensional Computingcited by 7
  9. 2021Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networkscited by 7
  10. 2020Cellular Automata Can Reduce Memory Requirements of Collective-State Computingcited by 6
  11. 2021A 5 μ W Standard Cell Memory-based Configurable Hyperdimensional Computing Accelerator for Always-on Smart Sensingcited by 6
  12. 2020Task-Projected Hyperdimensional Computing for Multi-Task Learningcited by 5
  13. 2020The Importance of Balanced Data Sets: Analyzing a Vehicle Trajectory Prediction Model based on Neural Networks and Distributed Representationscited by 3

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 0; 2024: 4.

8 papers.

  1. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challengescited by 69
  2. 2022Unpaired Image Translation via Vector Symbolic Architecturescited by 13
  3. 2024Generalized Holographic Reduced Representationscited by 6
  4. 2024Lifelong Intelligence Beyond the Edge using Hyperdimensional Computingcited by 5
  5. 2022Automated Architecture Search for Brain-inspired Hyperdimensional Computingcited by 3
  6. 2024Self-Attention Based Semantic Decomposition in Vector Symbolic Architecturescited by 2
  7. 2024Symbolic Disentangled Representations for Imagescited by 2
  8. 2022Computing with Hypervectors for Efficient Speaker Identificationcited by 0