A Theoretical Perspective on Hyperdimensional Computing

Abstract

Hyperdimensional (HD) computing is a set of neurally inspired methods for obtaining high-dimensional, low-precision, distributed representations of data. These representations can be combined with simple, neurally plausible algorithms to effect a variety of information processing tasks. HD computing has recently garnered significant interest from the computer hardware community as an energy-efficient, low-latency, and noise-robust tool for solving learning problems. In this review, we present a unified treatment of the theoretical foundations of HD computing with a focus on the suitability of representations for learning.

Updates with published version

References in corpus (2)

• Simple, Efficient, and Neural Algorithms for Sparse Coding
• Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters

Cited by in corpus (11)

• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations
• Vector Symbolic Architectures as a Computing Framework for Emerging Hardware
• Efficient Decoding of Compositional Structure in Holistic Representations
• HD-Bind: Encoding of Molecular Structure with Low Precision, Hyperdimensional Binary Representations
• Efficient Hyperdimensional Computing
• Hyperdimensional Representation Learning for Node Classification and Link Prediction
• Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware
• Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks
• On Design Choices in Similarity-Preserving Sparse Randomized Embeddings
• Cellular Automata Can Reduce Memory Requirements of Collective-State Computing
• Multiclass Linear Perceptrons with Multiplicative Margins