Vector Symbolic Architectures as a Computing Framework for Emerging Hardware

Abstract

This article reviews recent progress in the development of the computing framework vector symbolic architectures (VSA) (also known as hyperdimensional computing). This framework is well suited for implementation in stochastic, emerging hardware, and it naturally expresses the types of cognitive operations required for artificial intelligence (AI). We demonstrate in this article that the field-like algebraic structure of VSA offers simple but powerful operations on high-dimensional vectors that can support all data structures and manipulations relevant to modern computing. In addition, we illustrate the distinguishing feature of VSA, "computing in superposition," which sets it apart from conventional computing. It also opens the door to efficient solutions to the difficult combinatorial search problems inherent in AI applications. We sketch ways of demonstrating that VSA are computationally universal. We see them acting as a framework for computing with distributed representations that can play a role of an abstraction layer for emerging computing hardware. This article serves as a reference for computer architects by illustrating the philosophy behind VSA, techniques of distributed computing with them, and their relevance to emerging computing hardware, such as neuromorphic computing.

31 pages, 15 figures, 4 Tables

References in corpus (14)

• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations
• Robust High-dimensional Memory-augmented Neural Networks
• A Theoretical Perspective on Hyperdimensional Computing
• Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
• On the Turing Completeness of Modern Neural Network Architectures
• Superposition of many models into one
• Neural Distributed Autoassociative Memories: A Survey
• Shift-Equivariant Similarity-Preserving Hypervector Representations of Sequences
• Generalized Key-Value Memory to Flexibly Adjust Redundancy in Memory-Augmented Networks
• Implementing Turing Machines in Dynamic Field Architectures
• Integer Factorization with Compositional Distributed Representations
• Orthogonal Matrices for MBAT Vector Symbolic Architectures, and a "Soft" VSA Representation for JSON
• Graph Embeddings via Tensor Products and Approximately Orthonormal Codes

Cited by in corpus (7)

• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
• Neuromorphic Visual Scene Understanding with Resonator Networks
• Perceptron Theory Can Predict the Accuracy of Neural Networks
• Efficient Decoding of Compositional Structure in Holistic Representations
• Visual Odometry with Neuromorphic Resonator Networks
• Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware
• Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks