A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges

Author:

Kleyko Denis1ORCID,Rachkovskij Dmitri2ORCID,Osipov Evgeny3ORCID,Rahimi Abbas4ORCID

Affiliation:

1. University of California at Berkeley, USA Research Institutes of Sweden, Kista, Sweden

2. International Research and Training Center for Information Technologies,Ukraine Luleå University of Technology, Luleå, Sweden

3. Luleå University of Technology, Luleå, Sweden

4. IBM Research–Zurich, Zurich, Switzerland

Abstract

This is Part II of the two-part comprehensive survey devoted to a computing framework most commonly known under the names Hyperdimensional Computing and Vector Symbolic Architectures (HDC/VSA). Both names refer to a family of computational models that use high-dimensional distributed representations and rely on the algebraic properties of their key operations to incorporate the advantages of structured symbolic representations and vector distributed representations. Holographic Reduced Representations [ 321 , 326 ] is an influential HDC/VSA model that is well known in the machine learning domain and often used to refer to the whole family. However, for the sake of consistency, we use HDC/VSA to refer to the field. Part I of this survey [ 222 ] covered foundational aspects of the field, such as the historical context leading to the development of HDC/VSA, key elements of any HDC/VSA model, known HDC/VSA models, and the transformation of input data of various types into high-dimensional vectors suitable for HDC/VSA. This second part surveys existing applications, the role of HDC/VSA in cognitive computing and architectures, as well as directions for future work. Most of the applications lie within the Machine Learning/Artificial Intelligence domain; however, we also cover other applications to provide a complete picture. The survey is written to be useful for both newcomers and practitioners.

Funder

European Union’s Horizon 2020 Programme

Marie Skłodowska-Curie Individual

AFOSR

National Academy of Sciences of Ukraine

Ministry of Education and Science of Ukraine

Swedish Foundation for Strategic Research

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science,Theoretical Computer Science

Cited by 48 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Efficient Hyperdimensional Computing With Spiking Phasors;Neural Computation;2024-08-19

2. The blessing of dimensionality;Neurosymbolic Artificial Intelligence;2024-07-18

3. On Design Choices in Similarity-Preserving Sparse Randomized Embeddings;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

4. Vector Symbolic Sub-objects Classifiers as Manifold Analogues;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

5. AeneasHDC: An Automatic Framework for Deploying Hyperdimensional Computing Models on FPGAs;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3