Please use this identifier to cite or link to this item:
https://dspace.upt.ro/xmlui/handle/123456789/3853
Title: | Gradient algorithms with improved convergence [articol] |
Authors: | Partheniu, Cezar |
Subjects: | Gradient adaptive learning rate Adaptive filtering Generalized normalized gradient descent |
Issue Date: | 2004 |
Publisher: | Timişoara : Editura Politehnica |
Citation: | Partheniu, Cezar. Gradient algorithms with improved convergence. Timişoara: Editura Politehnica, 2004 |
Series/Report no.: | Buletinul ştiinţific al Universităţii „Politehnica” din Timişoara, România. Seria electronică şi telecomunicaţii, Tom 49(63), fasc. 2 (2004), p. 75-80 |
Abstract: | A generalized normalized gradient descend (GNGD) algorithm for linear finite-impulse response is presented and analized. The GNGD is an extension of the normalized least mean square (NLMS) algorithm by means of an additional gradient adaptive term in the denominator of the learning rate of NLMS. GNGD has better convergence in linear prediction configuration than other algorithms, good performances in system identification configuration in some conditions, worse response in interferences cancelling configuration and similar results with NLMS in reverse modelling configuration. |
URI: | http://primo.upt.ro:1701/primo-explore/search?query=any,contains,Gradient%20algorithms%20with%20improved%20convergence&tab=default_tab&search_scope=40TUT&vid=40TUT_V1&lang=ro_RO&offset=0 Link Primo |
Appears in Collections: | Articole științifice/Scientific articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
BUPT_ART__Partheniu_f.pdf | 755.61 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.