A survey on hyperdimensional computing aka vector symbolic architectures, part i: Models and data transformations

D Kleyko, DA Rachkovskij, E Osipov… - ACM Computing …, 2022 - dl.acm.org
This two-part comprehensive survey is devoted to a computing framework most commonly
known under the names Hyperdimensional Computing and Vector Symbolic Architectures …

A survey on hyperdimensional computing aka vector symbolic architectures, part ii: Applications, cognitive models, and challenges

D Kleyko, D Rachkovskij, E Osipov, A Rahimi - ACM Computing Surveys, 2023 - dl.acm.org
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 …

Constrained few-shot class-incremental learning

M Hersche, G Karunaratne… - Proceedings of the …, 2022 - openaccess.thecvf.com
Continually learning new classes from fresh data without forgetting previous knowledge of
old classes is a very challenging research problem. Moreover, it is imperative that such …

Vector symbolic architectures as a computing framework for emerging hardware

D Kleyko, M Davies, EP Frady, P Kanerva… - Proceedings of the …, 2022 - ieeexplore.ieee.org
This article reviews recent progress in the development of the computing framework vector
symbolic architectures (VSA)(also known as hyperdimensional computing). This framework …

Hyperseed: Unsupervised learning with vector symbolic architectures

E Osipov, S Kahawala, D Haputhanthri… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Motivated by recent innovations in biologically inspired neuromorphic hardware, this article
presents a novel unsupervised machine learning algorithm named Hyperseed that draws on …

Recent progress and development of hyperdimensional computing (hdc) for edge intelligence

CY Chang, YC Chuang, CT Huang… - IEEE Journal on …, 2023 - ieeexplore.ieee.org
Brain-inspired Hyperdimensional Computing (HDC) is an emerging framework in low-
energy designs for solving classification tasks at the edge. Unlike mainstream neural …

Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning

B Qi, J Gao, X Chen, D Li, J Liu, L Wu… - arXiv preprint arXiv …, 2024 - arxiv.org
Few-Shot Class-Incremental Learning (FSCIL) has gained considerable attention in recent
years for its pivotal role in addressing continuously arriving classes. However, it encounters …

Few-shot continual learning based on vector symbolic architectures

G Karunaratne, M Hersche, G Cherubini… - Compendium of …, 2023 - ebooks.iospress.nl
Abstract Vector Symbolic Architecture (VSA) is a powerful computing model that is built on a
rich algebra in which all representations—from atomic to composite structures—are high …

MSO‐DETR: Metric space optimization for few‐shot object detection

H Sima, M Wang, L Liu, Y Zhang… - CAAI Transactions on …, 2024 - Wiley Online Library
In the metric‐based meta‐learning detection model, the distribution of training samples in
the metric space has great influence on the detection performance, and this influence is …

Memory-Dependent Computation and Learning in Spiking Neural Networks Through Hebbian Plasticity

T Limbacher, O Özdenizci… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Spiking neural networks (SNNs) are the basis for many energy-efficient neuromorphic
hardware systems. While there has been substantial progress in SNN research, artificial …