přejít na obsah
Supervised learning with complex-valued neural networks Náhled dokumentu
ZavřítNáhled dokumentu
Checking...

Supervised learning with complex-valued neural networks

Autor Sundaram Suresh; Narasimhan Sundararajan; Ramasamy Savitha
Vydavatel: Berlin ; New York : Springer, ©2013.
Edice: Studies in computational intelligence, 421.
Vydání/formát:   book_digital : Document : EnglishZobrazit všechny vydání a formáty
Databáze:WorldCat
Zhrnutí:
Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks. Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to  Read more...
Rating:

(ještě nehodnoceno) 0 zobrazit recenze - Be the first.

Předmětová hesla:
Více podobných

 

Najít online exemplář

Odkazy na tento dokument

Vyhledat exemplář v knihovně

&AllPage.SpinnerRetrieving; Vyhledávaní knihoven, které vlastní tento dokument...

Detaily

Žánr/forma: Electronic books
Typ materiálu: Document, Internet resource
Typ dokumentu: Internet Resource, Computer File
Všichni autoři/tvůrci: Sundaram Suresh; Narasimhan Sundararajan; Ramasamy Savitha
ISBN: 9783642294914 364229491X
OCLC číslo: 805398598
Popis: 1 online resource.
Obsahy: Introduction --
Fully Complex-valued Multi Layer Perceptron Networks --
A Fully Complex-valued Radial Basis Function Network and Its Learning Algorithm --
Fully Complex-valued Relaxation Networks --
Performance Study on Complex-valued Function Approximation Problems --
Circular Complex-valued Extreme Learning Machine Classifier --
Performance Study on Real-valued Classification Problems --
Complex-valued Self-regulatory Resource Allocation Network (CSRAN).
Název edice: Studies in computational intelligence, 421.
Odpovědnost: Sundaram Suresh, Narasimhan Sundararajan, and Ramasamy Savitha.
Více informací:

Anotace:

A new generation of neural networks is needed in telecommunications, medical imaging and signal processing as signals become more complex and nonlinear. This survey of the latest complex-valued  Read more...

Reviews

User-contributed reviews
Retrieving GoodReads reviews...
Retrieving DOGObooks reviews...

Štítky

Buďte první.
Potvrdit tento požadavek

Tento dokument jste si již vyžádali. Prosím vyberte Ok pokud chcete přesto v žádance pokračovat.

Propojená data


<http://www.worldcat.org/oclc/805398598>
library:oclcnum"805398598"
library:placeOfPublication
library:placeOfPublication
library:placeOfPublication
owl:sameAs<info:oclcnum/805398598>
rdf:typeschema:Book
rdfs:seeAlso
schema:about
schema:about
schema:about
schema:about
schema:about
schema:author
schema:bookFormatschema:EBook
schema:contributor
rdf:typeschema:Person
schema:name"Sundararajan, Narasimhan."
schema:contributor
schema:copyrightYear"2013"
schema:datePublished"2013"
schema:description"Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks. Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to develop complex-valued neural networks and derive their learning algorithms to represent these signals at every step of the learning process. This monograph comprises a collection of new supervised learning algorithms along with novel architectures for complex-valued neural networks. The concepts of meta-cognition equipped with a self-regulated learning have been known to be the best human learning strategy. In this monograph, the principles of meta-cognition have been introduced for complex-valued neural networks in both the batch and sequential learning modes. For applications where the computation time of the training process is critical, a fast learning complex-valued neural network called as a fully complex-valued relaxation network along with its learning algorithm has been presented. The presence of orthogonal decision boundaries helps complex-valued neural networks to outperform real-valued networks in performing classification tasks. This aspect has been highlighted. The performances of various complex-valued neural networks are evaluated on a set of benchmark and real-world function approximation and real-valued classification problems."
schema:exampleOfWork<http://worldcat.org/entity/work/id/1149975527>
schema:inLanguage"en"
schema:name"Supervised learning with complex-valued neural networks"
schema:publisher
schema:url<http://dx.doi.org/10.1007/978-3-642-29491-4>
schema:url<http://site.ebrary.com/id/10656630>
schema:workExample
schema:workExample

Content-negotiable representations

Zavřít okno

Prosím přihlašte se do WorldCat 

Nemáte účet? Můžete si jednoduše vytvořit bezplatný účet.