Vector Symbolic Architecture

This article may be expanded with text translated from the corresponding article in English. Click [expand] for important translation instructions. Machine translation like DeepL or Google Translate is a useful starting point for translations, but translators must revise errors as necessary and confirm that the translation is accurate, rather than simply copy-pasting machine-translated text into the Simple English Wikipedia. Do not translate text that appears unreliable or low-quality. If possible, verify the text with references provided in the foreign-language article. You must provide copyright attribution in the edit summary accompanying your translation by providing an interlanguage link to the source of your translation. A model attribution edit summary Content in this edit is translated from the existing English Wikipedia article at [[:en:]]; see its history for attribution. You should also add the template {{Translated page}} to the talk page. For more guidance, see Wikipedia:Translation.

Vector Symbolic Architecture (VSA) is a kind of vector algebra used in an embedding space [en] to represent symbol manipulation [en] as vector operations.

It is also called hyperdimensional computing.

Its Turing completeness is not yet proven but a 2024 paper supports it since it has been found to be Cartesian closed [en].

HDC algebra reveals the logic of how and why systems makes decisions, unlike artificial neural networks. Physical world objects can be mapped to hypervectors, to be processed by the algebra.

History

Vector symbolic architectures (VSA) provided a systematic approach to high-dimensional symbol representations to support operations such as establishing relationships. Early examples include holographic reduced representations, binary spatter codes, and matrix binding of additive terms. HD computing advanced these models, particularly emphasizing hardware efficiency.

In 2015, Eric Weiss showed how to fully represent an image as a hypervector. A vector could contain information about all the objects in the image, including properties such as color, position, and size.

In 2023, Abbas Rahimi et al., used HDC with neural networks to solve Raven's progressive matrices.

In 2023, Mike Heddes et Al. under the supervision of Professors Givargis, Nicolau and Veidenbaum created a hyper-dimensional computing library that is built on top of PyTorch [en].

Related pages

• Lambda calculus
• Turing machine
• JEPA
• Word embedding
• Support vector machine [en]

References

• Kleyko, Denis; Rachkovskij, Dmitri A.; Osipov, Evgeny; Rahimi, Abbas (2023-07-31). "A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations". ACM Computing Surveys. 55 (6): 1–40. arXiv:2111.06077. doi:10.1145/3538531. ISSN 0360-0300.
• Kleyko, Denis; Rachkovskij, Dmitri; Osipov, Evgeny; Rahimi, Abbas (2023-09-30). "A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges". ACM Computing Surveys. 55 (9): 1–52. arXiv:2112.15424. doi:10.1145/3558000. ISSN 0360-0300.

External links

• Stock, M.; Van Criekinge, W.; Boeckaerts, D.; Taelman, S.; Van Haeverbeke, M.; Dewulf, P.; De Baets, B. (2024), Dutt, V. (ed.), "Hyperdimensional computing: a fast, robust, and interpretable paradigm for biological data", PLOS Computational Biology, 20 (9) e1012426, Public Library of Science (PLOS), arXiv:2402.17572, doi:10.1371/journal.pcbi.1012426, PMC 11421772, PMID 39316621
• Cumbo, F.; Chicco, D. (2025), "Hyperdimensional computing in biomedical sciences: a brief review", PeerJ Computer Science, 11 (e2885) e2885, doi:10.7717/peerj-cs.2885, PMC 12192801, PMID 40567746
• Kanerva, Pentti (2009-06-01). "Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors". Cognitive Computation. 1 (2): 139–159. doi:10.1007/s12559-009-9009-8. ISSN 1866-9964. S2CID 733980.
• Neubert, Peer; Schubert, Stefan; Protzel, Peter (2019-12-01). "An Introduction to Hyperdimensional Computing for Robotics". KI – Künstliche Intelligenz. 33 (4): 319–330. doi:10.1007/s13218-019-00623-z. ISSN 1610-1987. S2CID 202642163.
• Neubert, Peer; Schubert, Stefan (2021-01-19). "Hyperdimensional computing as a framework for systematic aggregation of image descriptors". arXiv:2101.07720v1 [cs.CV].
• Stock, Michiel (2022-10-04). "Tutorial on Hyperdimensional Computing". Retrieved 2023-07-29.

• "HD/VSA". www.hd-computing.com. 2023-03-13. Retrieved 2023-04-15.
• Ananthaswamy, Anil (2023-04-13). "A New Approach to Computation Reimagines Artificial Intelligence". Quanta Magazine. Retrieved 2023-06-13.