An adaptive Gauss-Newton algorithm for training multilayer nonlinear filters that have embedded memory

We describe herein a new means of training dynamic multilayer nonlinear adaptive filters, orneural networks. We restrict our discussion to multilayer dynamic Volterra networks, which are structured so as to restrict their degrees of computational freedom, based on a priori knowledge about the dynami...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Circuits, systems, and signal processing Ročník 18; číslo 4; s. 407 - 429
Hlavní autoři: Rabinowitz, M., Gutt, G. M., Franklin, G. F.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Heidelberg Springer 01.01.1999
Springer Nature B.V
Témata:
Adaptive filters
Algorithms
Applied sciences
Circuit properties
Dynamical systems
Electric, optical and optoelectronic circuits
Electronic circuits
Electronics
Exact sciences and technology
Frequency filters
Multilayers
Networks
Nonlinear dynamics
Nonlinearity
Training
Waveform
Adaptive algorithm
Non linear filter
Gauss Newton method
Optimization method
Block diagram
Modeling
Experimental result
Multimachine power system
Volterra series
Algorithm performance
Finite impulse response filter
Cost function
ISSN:0278-081X, 1531-5878
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We describe herein a new means of training dynamic multilayer nonlinear adaptive filters, orneural networks. We restrict our discussion to multilayer dynamic Volterra networks, which are structured so as to restrict their degrees of computational freedom, based on a priori knowledge about the dynamic operation to be emulated. The networks consist of linear dynamic filters together with nonlinear generalized single-layer subnets. We describe how a Newton-like optimization strategy can be applied to these dynamic architectures and detail a newmodified Gauss-Newton optimization technique. The new training algorithm converges faster and to a smaller value of cost than backpropagation-through-time for a wide range of adaptive filtering applications. We apply the algorithm to modeling the inverse of a nonlinear dynamic tracking system. The superior performance of the algorithm over standard techniques is demonstrated.[PUBLICATION ABSTRACT]
Bibliografie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0278-081X
1531-5878
DOI:10.1007/BF01200791