Hypervectors from Optical Disorder: Programmable Encoding and Optical Inference for Hyperdimensional Computing
Abstract
Hyperdimensional computing (HDC) is a computing framework that represents information as high-dimensional pseudorandom vectors called hypervectors (HVs), enabling learning and inference through simple algebraic operations. The HV dimensionality provides computational capacity and error robustness, but the required high-dimensional randomness must be stored or regenerated, imposing a memory--computation tradeoff. Here, we address this tradeoff by physically embodying the randomness required for HV generation in the static disorder of a scattering medium. Specifically, a silicon photonic circuit combined with the scattering medium generates high-dimensional HVs from a small number of input values in a single optical shot. Detector-side encoding programs HV correlations for continuous and categorical representations. The resulting HVs reproduce key statistical and compositional properties of ideal i.i.d.\ random HVs, including pairwise similarity statistics, associative-memory capacity, and factorization capacity. We further demonstrate an optically assisted inference path using the generated HVs and optical similarity evaluation.
Related
- Parameter-efficient neural computing with programmable photonic meshes
- Programmable Coherent Memory Kernels for Quantum Reservoir Computing in Waveguide QED
- A-GHOST: High-rate streaming of trigger-level data to programmable GPU inference
- Inference of Unknown Dynamical Components Using Next Generation Reservoir Computing: From Chaotic Systems to Climate Data
- Quantum Computing through Computational Imaging: Representations, Measurement, and Inference
BibTeX
@misc{iwata2026hypervectors,
title = {{Hypervectors from Optical Disorder: Programmable Encoding and Optical Inference for Hyperdimensional Computing}},
author = {Takuya Iwata and Namthip Srisuthep and Satoshi Sunada},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24108},
eprint = {2609.24108},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.24108},
}
RIS
TY - UNPB
TI - Hypervectors from Optical Disorder: Programmable Encoding and Optical Inference for Hyperdimensional Computing
AU - Takuya Iwata
AU - Namthip Srisuthep
AU - Satoshi Sunada
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.24108
UR - https://arxiv.org/abs/2609.24108
AB - Hyperdimensional computing (HDC) is a computing framework that represents information as high-dimensional pseudorandom vectors called hypervectors (HVs), enabling learning and inference through simple algebraic operations. The HV dimensionality provides computational capacity and error robustness, but the required high-dimensional randomness must be stored or regenerated, imposing a memory--computation tradeoff. Here, we address this tradeoff by physically embodying the randomness required for HV generation in the static disorder of a scattering medium. Specifically, a silicon photonic circuit combined with the scattering medium generates high-dimensional HVs from a small number of input values in a single optical shot. Detector-side encoding programs HV correlations for continuous and categorical representations. The resulting HVs reproduce key statistical and compositional properties of ideal i.i.d.\ random HVs, including pairwise similarity statistics, associative-memory capacity, and factorization capacity. We further demonstrate an optically assisted inference path using the generated HVs and optical similarity evaluation.
ER -