Sökning: id:"swepub:oai:DiVA.org:ltu-68400" >
Classification and ...
Classification and Recall With Binary Hyperdimensional Computing : Tradeoffs in Choice of Density and Mapping Characteristics
-
- Kleyko, Denis, 1990- (författare)
- Luleå tekniska universitet,Datavetenskap
-
- Rahimi, Abbas (författare)
- University of California at Berkeley, Berkeley
-
- Rachkovskij, Dmitri A. (författare)
- International Research and Training, Center for Information Technologies and Systems, Kiev, Ukraine
-
visa fler...
-
- Osipov, Evgeny (författare)
- Luleå tekniska universitet,Datavetenskap
-
- Rabaey, Jan M. (författare)
- University of California at Berkeley, Berkeley
-
visa färre...
-
(creator_code:org_t)
- IEEE, 2018
- 2018
- Engelska.
-
Ingår i: IEEE Transactions on Neural Networks and Learning Systems. - : IEEE. - 2162-237X .- 2162-2388. ; 29:12, s. 5880-5898
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Hyperdimensional (HD) computing is a promising paradigm for future intelligent electronic appliances operating at low power. This paper discusses tradeoffs of selecting parameters of binary HD representations when applied to pattern recognition tasks. Particular design choices include density of representations and strategies for mapping data from the original representation. It is demonstrated that for the considered pattern recognition tasks (using synthetic and real-world data) both sparse and dense representations behave nearly identically. This paper also discusses implementation peculiarities which may favor one type of representations over the other. Finally, the capacity of representations of various densities is discussed.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)
Nyckelord
- Dependable Communication and Computation Systems
- Kommunikations- och beräkningssystem
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas