“…Specifically, hypervector representation is (1) holographic , that information is distributed evenly across components of the hypervector (Kleyko et al, 2023 ), (2) robust , that hypervectors are extremely noise tolerant as a natural result of hypervector redundancy (Kanerva, 2009 ; Poduval et al, 2022b ; Barkam et al, 2023a ), and (3) simple , that only lightweight operations are needed to perform learning tasks (Hernandez-Cane et al, 2021 ; Ni et al, 2022b ). In addition, the ability for hypervectors to operate symbolically through simple arithmetic has granted HDC the ability to perform cognitive tasks in a transparent and compositional way, e.g., memorization, learning, and association (Poduval et al, 2022a ; Hersche et al, 2023 ). Given the importance of the properties aforementioned, most HDC frameworks have a dedicated and specially designed HDC encoder for mapping original inputs to corresponding hypervectors.…”