SHEARer: Highly-Efficient Hyperdimensional Computing by Software-Hardware Enabled Multifold Approximation

Sahand Salamat
Sahand Salamat
Anthony Thomas
Anthony Thomas
Fatemeh Asgarinejad
Fatemeh Asgarinejad

ISLPED '20: ACM/IEEE International Symposium on Low Power Electronics and Design Boston Massachusetts August, 2020, pp. 241-246, 2020.

Cited by: 0|Bibtex|Views28|DOI:https://doi.org/10.1145/3370748.3406587
EI
Other Links: arxiv.org|dl.acm.org|dblp.uni-trier.de|academic.microsoft.com

Abstract:

Hyperdimensional computing (HD) is an emerging paradigm for machine learning based on the evidence that the brain computes on high-dimensional, distributed, representations of data. The main operation of HD is encoding, which transfers the input data to hyperspace by mapping each input feature to a hypervector, followed by a bundling proc...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments