A survey on hyperdimensional computing aka vector symbolic architectures, part ii: Applications, cognitive models, and challenges
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 …
commonly known under the names Hyperdimensional Computing and Vector Symbolic …
Vector symbolic architectures as a computing framework for emerging hardware
This article reviews recent progress in the development of the computing framework vector
symbolic architectures (VSA)(also known as hyperdimensional computing). This framework …
symbolic architectures (VSA)(also known as hyperdimensional computing). This framework …
In-memory hyperdimensional computing
Hyperdimensional computing is an emerging computational framework that takes inspiration
from attributes of neuronal circuits including hyperdimensionality, fully distributed …
from attributes of neuronal circuits including hyperdimensionality, fully distributed …
Classification and recall with binary hyperdimensional computing: Tradeoffs in choice of density and mapping characteristics
Hyperdimensional (HD) computing is a promising paradigm for future intelligent electronic
appliances operating at low power. This paper discusses tradeoffs of selecting parameters …
appliances operating at low power. This paper discusses tradeoffs of selecting parameters …
Formation of similarity-reflecting binary vectors with random binary projections
DA Rachkovskij - Cybernetics and Systems Analysis, 2015 - Springer
We propose a transformation of real input vectors to output binary vectors by projection
using a binary random matrix with elements {0, 1} and thresholding. We investigate the rate …
using a binary random matrix with elements {0, 1} and thresholding. We investigate the rate …
Neural distributed autoassociative memories: A survey
VI Gritsenko, DA Rachkovskij, AA Frolov… - arXiv preprint arXiv …, 2017 - arxiv.org
Introduction. Neural network models of autoassociative, distributed memory allow storage
and retrieval of many items (vectors) where the number of stored items can exceed the …
and retrieval of many items (vectors) where the number of stored items can exceed the …
Wireless on-chip communications for scalable in-memory hyperdimensional computing
Hyperdimensional computing (HDC) is an emerging computing paradigm that represents,
manipulates, and communicates data using very long random vectors (aka hypervectors) …
manipulates, and communicates data using very long random vectors (aka hypervectors) …
Building a world model with structure-sensitive sparse binary distributed representations
We present a new cognitive architecture named Associative-Projective Neural Networks
(APNNs). APNNs have a multi-module, multi-level, and multi-modal design that works with …
(APNNs). APNNs have a multi-module, multi-level, and multi-modal design that works with …
Binary vectors for fast distance and similarity estimation
DA Rachkovskij - Cybernetics and Systems Analysis, 2017 - Springer
This review considers methods and algorithms for fast estimation of distance/similarity
measures between initial data from vector representations with binary or integer-valued …
measures between initial data from vector representations with binary or integer-valued …
Estimation of vectors similarity by their randomized binary projections
DA Rachkovskij - Cybernetics and Systems Analysis, 2015 - Springer
We analyze the estimation of the angle, scalar product, and the Euclidean distance of real-
valued vectors using binary vectors with controlled sparsity. Transformation is carried out by …
valued vectors using binary vectors with controlled sparsity. Transformation is carried out by …