TY - JOUR
T1 - Measuring the Storing Capacity of Hyperdimensional Binary Vectors
AU - Quiroz Mercado, Job Isaías
AU - Fernández, Ricardo Barrón
AU - Ramírez Salinas, Marco Antonio
N1 - Publisher Copyright:
© 2022 Instituto Politecnico Nacional. All rights reserved.
PY - 2022
Y1 - 2022
N2 - Hyperdimensional computing is a model of computation based on the properties of high-dimensional vectors. It combines characteristics from artificial neural networks and symbolic computing. The area where hyperdimensional computing can be applied is natural language processing, where vector representations are already present in the form of word embedding models. However, hyperdimensional computing encodes information differently, its representations can include the distributional information of a word in a given context and it can also account for its semantic features. In this work, we investigate the storing capacity of hyperdimensional binary vectors. We present two different configurations in which semantic features can be encoded and measure how many can be stored, and later retrieved, within a single vector. The results presented in this work lay the foundation to develop a concept representation model with hyperdimensional computation.
AB - Hyperdimensional computing is a model of computation based on the properties of high-dimensional vectors. It combines characteristics from artificial neural networks and symbolic computing. The area where hyperdimensional computing can be applied is natural language processing, where vector representations are already present in the form of word embedding models. However, hyperdimensional computing encodes information differently, its representations can include the distributional information of a word in a given context and it can also account for its semantic features. In this work, we investigate the storing capacity of hyperdimensional binary vectors. We present two different configurations in which semantic features can be encoded and measure how many can be stored, and later retrieved, within a single vector. The results presented in this work lay the foundation to develop a concept representation model with hyperdimensional computation.
KW - Hyperdimensional computing
KW - reduced representations
KW - vector symbolic architectures
UR - http://www.scopus.com/inward/record.url?scp=85135744179&partnerID=8YFLogxK
U2 - 10.13053/CyS-26-2-3343
DO - 10.13053/CyS-26-2-3343
M3 - Artículo
AN - SCOPUS:85135744179
SN - 1405-5546
VL - 26
SP - 1027
EP - 1033
JO - Computacion y Sistemas
JF - Computacion y Sistemas
IS - 2
ER -