Classification using Hyperdimensional Computing: A Review

Abstract

Hyperdimensional (HD) computing is built upon its unique data type referred to as hypervectors. The dimension of these hypervectors is typically in the range of tens of thousands. Proposed to solve cognitive tasks, HD computing aims at calculating similarity among its data. Data transformation is realized by three operations, including addition, multiplication and permutation. Its ultra-wide data representation introduces redundancy against noise. Since information is evenly distributed over every bit of the hypervectors, HD computing is inherently robust. Additionally, due to the nature of those three operations, HD computing leads to fast learning ability, high energy efficiency and acceptable accuracy in learning and classification tasks. This paper introduces the background of HD computing, and reviews the data representation, data transformation, and similarity measurement. The orthogonality in high dimensions presents opportunities for flexible computing. To balance the tradeoff between accuracy and efficiency, strategies include but are not limited to encoding, retraining, binarization and hardware acceleration. Evaluations indicate that HD computing shows great potential in addressing problems using data in the form of letters, signals and images. HD computing especially shows significant promise to replace machine learning algorithms as a light-weight classifier in the field of internet of things (IoTs).

arXiv commentIEEE Circuits and Systems Magazine (2020)

References in corpus (1)

• Holographic Graph Neuron: a Bio-Inspired Architecture for Pattern Processing

Cited by in corpus (19)

• 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
• Perceptron Theory Can Predict the Accuracy of Neural Networks
• Computational Associative Memory with Amorphous InGaZnO Channel 3D NAND-Compatible FG Transistors
• Training a HyperDimensional Computing Classifier using a Threshold on its Confidence
• Brain-Inspired Hyperdimensional Computing: How Thermal-Friendly for Edge Computing?
• HDXplore: Automated Blackbox Testing of Brain-Inspired Hyperdimensional Computing
• Brain-inspired Cognition in Next Generation Racetrack Memories
• HD-Bind: Encoding of Molecular Structure with Low Precision, Hyperdimensional Binary Representations
• Robust Clustering using Hyperdimensional Computing
• Optical hyperdimensional soft sensing: Speckle-based touch interface and tactile sensor
• Hyperdimensional Representation Learning for Node Classification and Link Prediction
• Integer Factorization with Compositional Distributed Representations
• On Design Choices in Similarity-Preserving Sparse Randomized Embeddings
• Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computing
• FactorHD: A Hyperdimensional Computing Model for Multi-Object Multi-Class Representation and Factorization
• Multiclass Linear Perceptrons with Multiplicative Margins
• Graph Neural Networks Based Analog Circuit Link Prediction
• Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks