Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.1
3.7
Journals
BDCC
Special Issues
Brain-Inspired Hyperdimensional Computing: Theoretical Perspectives and Real-World Applications
share announcement

Brain-Inspired Hyperdimensional Computing: Theoretical Perspectives and Real-World Applications

A special issue of Big Data and Cognitive Computing (ISSN 2504-2289).

Deadline for manuscript submissions: closed (31 October 2024) | Viewed by 1136

Special Issue Editors

Dr. Fabio Cumbo

E-Mail Website
Guest Editor
Center for Computational Life Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH 44195, USA
Interests: computational biology; machine learning; metagenomics; microbial genomics; vector-symbolic architectures; hyperdimensional computing
Dr. Jayadev Joshi

E-Mail Website
Guest Editor
Center for Computational Life Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH 44195, USA
Interests: machine learning; hyperdimensional computing; reproducible multi-omics data analysis workflow and pipelines development
Dr. Bryan Raubenolt

E-Mail Website
Guest Editor
Center for Computational Life Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH 44195, USA
Interests: molecular dynamics simulations; computational chemistry; quantum computing; protein structure prediction; cheminformatics software development
Dr. Rahul Shubhra Mandal

E-Mail Website
Guest Editor
Perelman School of Medicine, Department of Cancer Biology, University of Pennsylvania, Philadelphia, PA 19104, USA
Interests: computational genomics and proteomics; structural bioinformatics; machine learning

Special Issue Information

Dear Colleagues,

This Special Issue aims to explore the emerging field of hyperdimensional computing (HDC, a.k.a. vector-symbolic architectures), inspired by the way in which the human brain remembers and processes information, leveraging vectors in a high-dimensional space and a set of arithmetic operations. This publication will delve into the theoretical foundations, methodologies, algorithms, and practical applications of hyperdimensional computing, fostering a deeper understanding of its potential impact in the management of big data and cognitive computing. This Special Issue seeks to encompass a wide array of topics related to HDC, with the objective of providing a comprehensive overview of the theoretical underpinnings and practical applications of this novel computational paradigm. We invite researchers worldwide to share their latest research on HDC. We are particularly interested in papers that present new theoretical insights, innovative algorithms, and real-world applications.

The scope includes, but is not limited to:

  • Theoretical frameworks and models underpinning hyperdimensional computing;
  • Arithmetic and mathematical foundations of hyperdimensional spaces for data representation and processing;
  • Hyperdimensional computing techniques for feature extraction, classification, and clustering;
  • Applications of hyperdimensional computing in natural language processing, computer vision, and speech recognition, and other domains where it can be applied to solve specific scientific problems;
  • Integration of hyperdimensional computing with cognitive computing for enhanced artificial intelligence capabilities;
  • Hardware implementations and optimizations to accelerate hyperdimensional computing tasks;
  • Comparative analysis of hyperdimensional computing with traditional computing paradigms in terms of performance, scalability, and efficiency;
  • Use cases and success stories demonstrating the practical utility of hyperdimensional computing in real-world scenarios.

Dr. Fabio Cumbo
Dr. Jayadev Joshi
Dr. Bryan Raubenolt
Dr. Rahul Shubhra Mandal
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Big Data and Cognitive Computing is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • hyperdimensional computing
  • vector symbolic architectures
  • neuromorphic computing
  • cognitive computing
  • brain-inspired computing

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

22 pages, 9553 KiB  
Article
Margin-Based Training of HDC Classifiers
by Laura Smets, Dmitri Rachkovskij, Evgeny Osipov, Werner Van Leekwijck, Olexander Volkov and Steven Latré
Big Data Cogn. Comput. 2025, 9(3), 68; https://doi.org/10.3390/bdcc9030068 - 14 Mar 2025
Viewed by 424
Abstract
The explicit kernel transformation of input data vectors to their distributed high-dimensional representations has recently been receiving increasing attention in the field of hyperdimensional computing (HDC). The main argument is that such representations endow simpler last-leg classification models, often referred to as HDC [...] Read more.
The explicit kernel transformation of input data vectors to their distributed high-dimensional representations has recently been receiving increasing attention in the field of hyperdimensional computing (HDC). The main argument is that such representations endow simpler last-leg classification models, often referred to as HDC classifiers. HDC models have obvious advantages over resource-intensive deep learning models for use cases requiring fast, energy-efficient computations both for model training and deploying. Recent approaches to training HDC classifiers have primarily focused on various methods for selecting individual learning rates for incorrectly classified samples. In contrast to these methods, we propose an alternative strategy where the decision to learn is based on a margin applied to the classifier scores. This approach ensures that even correctly classified samples within the specified margin are utilized in training the model. This leads to improved test performances while maintaining a basic learning rule with a fixed (unit) learning rate. We propose and empirically evaluate two such strategies, incorporating either an additive or multiplicative margin, on the standard subset of the UCI collection, consisting of 121 datasets. Our approach demonstrates superior mean accuracy compared to other HDC classifiers with iterative error-correcting training. Full article
(This article belongs to the Special Issue Brain-Inspired Hyperdimensional Computing: Theoretical Perspectives and Real-World Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop