Please use this identifier to cite or link to this item:
|Title:||Trade-offs in the distribution of neural networks in a wireless sensor network||Authors:||Holenderski, M.
|Issue Date:||2005||Citation:||Holenderski, 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.||Abstract:||This 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.||Source Title:||Proceedings of the 2005 Intelligent Sensors, Sensor Networks and Information Processing Conference||URI:||http://scholarbank.nus.edu.sg/handle/10635/72069||ISBN:||0780393996|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Mar 30, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.