Linear Codes for Hyperdimensional Computing
N Raviv - Neural Computation, 2024 - direct.mit.edu
Hyperdimensional computing (HDC) is an emerging computational paradigm for
representing compositional information as high-dimensional vectors and has a promising …
representing compositional information as high-dimensional vectors and has a promising …
Gluing neural networks symbolically through hyperdimensional computing
Hyperdimensional Computing affords simple, yet powerful operations to create long
Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for …
Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for …
Gluing neural networks symbolically through hyperdimensional computing
D Yuan, D Summer-Stay, C Fermuller… - … of International Joint …, 2022 - par.nsf.gov
Hyperdimensional Computing affords simple, yet powerful operations to create long
Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for …
Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for …
Learning from hypervectors: A survey on hypervector encoding
Hyperdimensional computing (HDC) is an emerging computing paradigm that imitates the
brain's structure to offer a powerful and efficient processing and learning model. In HDC, the …
brain's structure to offer a powerful and efficient processing and learning model. In HDC, the …
Streaming encoding algorithms for scalable hyperdimensional computing
A Thomas, B Khaleghi, GK Jha, S Dasgupta… - arXiv preprint arXiv …, 2022 - arxiv.org
Hyperdimensional computing (HDC) is a paradigm for data representation and learning
originating in computational neuroscience. HDC represents data as high-dimensional, low …
originating in computational neuroscience. HDC represents data as high-dimensional, low …
Efficient decoding of compositional structure in holistic representations
We investigate the task of retrieving information from compositional distributed
representations formed by hyperdimensional computing/vector symbolic architectures and …
representations formed by hyperdimensional computing/vector symbolic architectures and …
Sobol Sequence Optimization for Hardware-Efficient Vector Symbolic Architectures
Hyperdimensional computing (HDC) is an emerging computing paradigm with significant
promise for efficient and robust learning. In HDC, objects are encoded with high …
promise for efficient and robust learning. In HDC, objects are encoded with high …
Advancing Hyperdimensional Computing Based on Trainable Encoding and Adaptive Training for Efficient and Accurate Learning
Hyperdimensional computing (HDC) is a computing paradigm inspired by the mechanisms
of human memory, characterizing data through high-dimensional vector representations …
of human memory, characterizing data through high-dimensional vector representations …
Brain-inspired Hyperdimensional Computing: Algorithms, models, and architectures
X Jiao, A Rahimi, C Fermüller… - Frontiers in …, 2022 - frontiersin.org
The field of Hyperdimensional (HD) Computing, aka Vector Symbolic Architectures (VSA), is
founded on the notion that the mind can be modeled by computing with high-dimensional …
founded on the notion that the mind can be modeled by computing with high-dimensional …
Unleashing Hyperdimensional Computing with Nyström Method based Encoding
Hyperdimensional computing (HDC) is an approach for solving cognitive information
processing tasks using data represented as high dimensional, low-precision, vectors. The …
processing tasks using data represented as high dimensional, low-precision, vectors. The …