1. ScholarBank@NUS
  2. 1. Staff
  3. Staff Publications
Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/72069
DC FieldValue
dc.titleTrade-offs in the distribution of neural networks in a wireless sensor network
dc.contributor.authorHolenderski, M.
dc.contributor.authorLukkien, J.
dc.contributor.authorTham, C.K.
dc.date.accessioned2014-06-19T03:31:05Z
dc.date.available2014-06-19T03:31:05Z
dc.date.issued2005
dc.identifier.citationHolenderski, M.,Lukkien, J.,Tham, C.K. (2005). Trade-offs in the distribution of neural networks in a wireless sensor network. Proceedings of the 2005 Intelligent Sensors, Sensor Networks and Information Processing Conference 2005 : 259-264. ScholarBank@NUS Repository.
dc.identifier.isbn0780393996
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/72069
dc.description.abstractThis article investigates the tradeoff between communication and memory usage in different methods of distributing neural networks in a Wireless Sensor Network. A structural approach is presented, categorized in two dimensions: horizontal and vertical decomposition. Horizontal decomposition turns out to be more attractive, due to high reuse of data present at the processor node. General properties of an alternative sematic approach are suggested theoretically allowing to dramatically increase efficiency. © 2005 IEEE.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.sourcetitleProceedings of the 2005 Intelligent Sensors, Sensor Networks and Information Processing Conference
dc.description.volume2005
dc.description.page259-264
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.