Tensor Products and Hyperdimensional Computing

Frank Qiu
5/17/2023
stat.MLcs.LG

No confident code implementation found for this paper.

Abstract

Following up on a previous analysis of graph embeddings, we generalize and expand some results to the general setting of vector symbolic architectures (VSA) and hyperdimensional computing (HDC). Importantly, we explore the mathematical relationship between superposition, orthogonality, and tensor product. We establish the tensor product representation as the central representation, with a suite of unique properties. These include it being the most general and expressive representation, as well as being the most compressed representation that has errorrless unbinding and detection.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Capacity Analysis of Vector Symbolic Architectures

81% match2023

Tensor Cookbook: Mastering Tensors through Diagrams

79% match2026

Fully tensorial approach to hypercomplex neural networks

78% match2024

Comb Tensor Networks vs. Matrix Product States: Enhanced Efficiency in High-Dimensional Spaces

78% match1 repo42024

Projected Tensor-Tensor Products for Efficient Computation of Optimal Multiway Data Representations

77% match1 repo22024

Developing a Foundation of Vector Symbolic Architectures Using Category Theory

77% match2025

Cite this paper

@article{qiu2023tensor,
  title  = {Tensor Products and Hyperdimensional Computing},
  author = {Frank Qiu},
  year   = {2023},
  eprint = {2305.10572},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.10572v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.10572.svg)](https://codeofpaper.com/paper/2305.10572)

Discussion