Imagen del editor

Supervised Learning with Complex-valued Neural Networks (Hardback)

Suresh Sundaram, Narasimhan Sundararajan, Ramasamy Savitha

0 valoraciones por Goodreads
ISBN 10: 3642294901 / ISBN 13: 9783642294907
Editorial: Springer-Verlag Berlin and Heidelberg GmbH & Co. KG, Germany, 2012
Nuevos Condición: New Encuadernación de tapa dura
Librería: The Book Depository EURO (London, Reino Unido)

Librería en AbeBooks desde: 29 de abril de 2014 Valoración librería Valoración 3 estrellas

Cantidad disponible: 1

Comprar nuevo
Precio: EUR 208,63 Convertir moneda
Gastos de envío: EUR 3,58 De Reino Unido a Estados Unidos de America Destinos, gastos y plazos de envío
Añadir al carrito

Descripción

Language: English. Brand new Book. 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. N° de ref. de la librería LIB9783642294907

Hacer una pregunta a la librería

Detalles bibliográficos

Título: Supervised Learning with Complex-valued ...

Editorial: Springer-Verlag Berlin and Heidelberg GmbH & Co. KG, Germany

Año de publicación: 2012

Encuadernación: Hardback

Condición del libro: New

Edición: 2013 ed.

Acerca de

Sinopsis:

Book by Suresh Sundaram Sundararajan Narasimhan Savitha Ra

Reseña del editor:

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.

"Sobre este título" puede pertenecer a otra edición de este libro.

Descripción de la librería

The Book Depository - bookdepository.com - is the UK's largest dedicated online bookseller offering the largest range of titles in the world, available for dispatch within 48 hours. Founded in 2004 to make 'All Books To All' we focus on selling 'less of more' rather than 'more of less', differentiating ourself from other retailers who increasingly focus on bestsellers. All books available to All Currently, The Book Depository is able to ship over 4 million unique titles, within 48 hours, from our fulfillment centre in Gloucester, United Kingdom. This figure is increasing everyday. Apart from publishers, distributors and wholesalers, we even list and supply books from other retailers!

Ver la página web de la librería

Condiciones de venta:

All books are shipped in New condition promptly, we are
happy to accept returns up to 30 days from purchase. Orders
usually ship within 1-2 business days. Domestic Shipments
are sent by Royal Mail, and International by Priority
Airmail. We are happy to accept returns up to 30 days from
purchase.

¿ Name of business : The Book Depository Ltd
¿ Form of legal entity : A Limited Company
¿ Business address: The Book Depository, Thames Central, Hatfield Road,
Slough, Berkshire, SL1 1QE
¿ Email address:...

Más información
Condiciones de envío:

Orders usually ship within 1-2 business days. Domestic Shipments are sent by Royal
Mail, and International by Priority Airmail. Orders usually ship within 1-2
business days. Domestic Shipments are sent by Royal Mail, and International by
Priority Airmail. We are happy to accept returns up to 30 days from purchase.
Please contact the seller directly if you wish to return an order.

Todos los libros de esta librería

Métodos de pago
aceptados por la librería

Visa Mastercard American Express Carte Bleue