Articles liés à Functional Networks with Applications: A Neural-Based...
Synopsis
Artificial neural networks have been recognized as a powerful tool to learn and reproduce systems in various fields of applications. Neural net- works are inspired by the brain behavior and consist of one or several layers of neurons, or computing units, connected by links. Each artificial neuron receives an input value from the input layer or the neurons in the previ- ous layer. Then it computes a scalar output from a linear combination of the received inputs using a given scalar function (the activation function), which is assumed the same for all neurons. One of the main properties of neural networks is their ability to learn from data. There are two types of learning: structural and parametric. Structural learning consists of learning the topology of the network, that is, the number of layers, the number of neurons in each layer, and what neurons are connected. This process is done by trial and error until a good fit to the data is obtained. Parametric learning consists of learning the weight values for a given topology of the network. Since the neural functions are given, this learning process is achieved by estimating the connection weights based on the given information. To this aim, an error function is minimized using several well known learning methods, such as the backpropagation algorithm. Unfortunately, for these methods: (a) The function resulting from the learning process has no physical or engineering interpretation. Thus, neural networks are seen as black boxes.
Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.
Acheter neuf
Afficher cet article
EUR 92,27
EUR 9,70 expédition depuis Allemagne vers France
Destinations, frais et délais
Résultats de recherche pour Functional Networks with Applications: A Neural-Based...
Image fournie par le vendeur
Functional Networks with Applications
Vendeur : moluna, Greven, Allemagne
Évaluation du vendeur 5 sur 5 étoiles
Etat : New. N° de réf. du vendeur 4195691
Quantité disponible : Plus de 20 disponibles
Image fournie par le vendeur
Functional Networks with Applications
impression à la demandeVendeur : BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Allemagne
Évaluation du vendeur 5 sur 5 étoiles
Taschenbuch. Etat : Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Artificial neural networks have been recognized as a powerful tool to learn and reproduce systems in various fields of applications. Neural net works are inspired by the brain behavior and consist of one or several layers of neurons, or computing units, connected by links. Each artificial neuron receives an input value from the input layer or the neurons in the previ ous layer. Then it computes a scalar output from a linear combination of the received inputs using a given scalar function (the activation function), which is assumed the same for all neurons. One of the main properties of neural networks is their ability to learn from data. There are two types of learning: structural and parametric. Structural learning consists of learning the topology of the network, that is, the number of layers, the number of neurons in each layer, and what neurons are connected. This process is done by trial and error until a good fit to the data is obtained. Parametric learning consists of learning the weight values for a given topology of the network. Since the neural functions are given, this learning process is achieved by estimating the connection weights based on the given information. To this aim, an error function is minimized using several well known learning methods, such as the backpropagation algorithm. Unfortunately, for these methods: (a) The function resulting from the learning process has no physical or engineering interpretation. Thus, neural networks are seen as black boxes. 324 pp. Englisch. N° de réf. du vendeur 9781461375623
Quantité disponible : 2 disponible(s)
Image d'archives
Functional Networks with Applications: A Neural-Based Paradigm (The Springer International Series in Engineering and Computer Science)
Vendeur : Ria Christie Collections, Uxbridge, Royaume-Uni
Évaluation du vendeur 5 sur 5 étoiles
Etat : New. In. N° de réf. du vendeur ria9781461375623_new
Quantité disponible : Plus de 20 disponibles
Image fournie par le vendeur
Functional Networks with Applications
Edité par
Springer US, Springer New York Feb 2013, 2013
ISBN 10 : 1461375622
ISBN 13 : 9781461375623
Neuf
Taschenbuch
Vendeur : buchversandmimpf2000, Emtmannsberg, BAYE, Allemagne
Évaluation du vendeur 5 sur 5 étoiles
Taschenbuch. Etat : Neu. This item is printed on demand - Print on Demand Titel. Neuware -Artificial neural networks have been recognized as a powerful tool to learn and reproduce systems in various fields of applications. Neural net works are inspired by the brain behavior and consist of one or several layers of neurons, or computing units, connected by links. Each artificial neuron receives an input value from the input layer or the neurons in the previ ous layer. Then it computes a scalar output from a linear combination of the received inputs using a given scalar function (the activation function), which is assumed the same for all neurons. One of the main properties of neural networks is their ability to learn from data. There are two types of learning: structural and parametric. Structural learning consists of learning the topology of the network, that is, the number of layers, the number of neurons in each layer, and what neurons are connected. This process is done by trial and error until a good fit to the data is obtained. Parametric learning consists of learning the weight values for a given topology of the network. Since the neural functions are given, this learning process is achieved by estimating the connection weights based on the given information. To this aim, an error function is minimized using several well known learning methods, such as the backpropagation algorithm. Unfortunately, for these methods: (a) The function resulting from the learning process has no physical or engineering interpretation. Thus, neural networks are seen as black boxes.Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg 324 pp. Englisch. N° de réf. du vendeur 9781461375623
Quantité disponible : 1 disponible(s)
Image fournie par le vendeur
Functional Networks with Applications : A Neural-Based Paradigm
Vendeur : AHA-BUCH GmbH, Einbeck, Allemagne
Évaluation du vendeur 5 sur 5 étoiles
Taschenbuch. Etat : Neu. Druck auf Anfrage Neuware - Printed after ordering - Artificial neural networks have been recognized as a powerful tool to learn and reproduce systems in various fields of applications. Neural net works are inspired by the brain behavior and consist of one or several layers of neurons, or computing units, connected by links. Each artificial neuron receives an input value from the input layer or the neurons in the previ ous layer. Then it computes a scalar output from a linear combination of the received inputs using a given scalar function (the activation function), which is assumed the same for all neurons. One of the main properties of neural networks is their ability to learn from data. There are two types of learning: structural and parametric. Structural learning consists of learning the topology of the network, that is, the number of layers, the number of neurons in each layer, and what neurons are connected. This process is done by trial and error until a good fit to the data is obtained. Parametric learning consists of learning the weight values for a given topology of the network. Since the neural functions are given, this learning process is achieved by estimating the connection weights based on the given information. To this aim, an error function is minimized using several well known learning methods, such as the backpropagation algorithm. Unfortunately, for these methods: (a) The function resulting from the learning process has no physical or engineering interpretation. Thus, neural networks are seen as black boxes. N° de réf. du vendeur 9781461375623
Quantité disponible : 1 disponible(s)
Image d'archives
Functional Networks with Applications: A Neural-Based Paradigm (The Springer International Series in Engineering and Computer Science)
Vendeur : Chiron Media, Wallingford, Royaume-Uni
Évaluation du vendeur 4 sur 5 étoiles
Paperback. Etat : New. N° de réf. du vendeur 6666-IUK-9781461375623
Quantité disponible : 10 disponible(s)
Image d'archives
Functional Networks with Applications: A Neural-Based Paradigm
Edité par
Springer-Verlag New York Inc., 2013
ISBN 10 : 1461375622
ISBN 13 : 9781461375623
Neuf
Paperback / softback
Vendeur : THE SAINT BOOKSTORE, Southport, Royaume-Uni
Évaluation du vendeur 5 sur 5 étoiles
Paperback / softback. Etat : New. This item is printed on demand. New copy - Usually dispatched within 5-9 working days 484. N° de réf. du vendeur C9781461375623
Quantité disponible : Plus de 20 disponibles
Image d'archives
Functional Networks with Applications: A Neural-Based Paradigm (The Springer International Series in Engineering and Computer Science)
Vendeur : Revaluation Books, Exeter, Royaume-Uni
Évaluation du vendeur 5 sur 5 étoiles
Paperback. Etat : Brand New. 320 pages. 9.25x6.10x0.73 inches. In Stock. N° de réf. du vendeur x-1461375622
Quantité disponible : 2 disponible(s)
Image d'archives
Functional Networks with Applications: A Neural-Based Paradigm (The Springer International Series in Engineering and Computer Science)
Vendeur : Lucky's Textbooks, Dallas, TX, Etats-Unis
Évaluation du vendeur 5 sur 5 étoiles
Etat : New. N° de réf. du vendeur ABLIING23Mar2716030034015
Quantité disponible : Plus de 20 disponibles
Image d'archives
Functional Networks with Applications: A Neural-Based Paradigm (The Springer International Series in Engineering and Computer Science)
Vendeur : Best Price, Torrance, CA, Etats-Unis
Évaluation du vendeur 4 sur 5 étoiles
Etat : New. SUPER FAST SHIPPING. N° de réf. du vendeur 9781461375623
Quantité disponible : 2 disponible(s)