An Extension to Basis-Hypervectors for Learning from Circular Data in Hyperdimensional Computing

Hyperdimensional Computing (HDC) is a computation framework based on random vector spaces, particularly useful for machine learning in resource-constrained environments. The encoding of information to the hyperspace is the most important stage in HDC. At its heart are basis-hypervectors, responsible...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2023 60th ACM/IEEE Design Automation Conference (DAC) s. 1 - 6
Hlavní autoři: Nunes, Igor, Heddes, Mike, Givargis, Tony, Nicolau, Alexandru
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 09.07.2023
Témata:
basis-hypervectors
circular data
Computational modeling
Data models
Design automation
Encoding
Heart
hyperdimensional computing
information theory
Machine learning
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Hyperdimensional Computing (HDC) is a computation framework based on random vector spaces, particularly useful for machine learning in resource-constrained environments. The encoding of information to the hyperspace is the most important stage in HDC. At its heart are basis-hypervectors, responsible for representing atomic information. We present a detailed study on basis-hypervectors, leading to broad contributions to HDC: 1) an improvement for level-hypervectors, used to encode real numbers; 2) a method to learn from circular data, an important type of information never before addressed in HDC. Results indicate that these contributions lead to considerably more accurate models for classification and regression.
DOI:10.1109/DAC56929.2023.10247736