9789819806621 - equivariant and coordinate independent convolutional networks: a gauge field theory of neural networks par weiler, maurice; forre, patrick; verlinde, erik; welling, max (16 résultats)
Equivariant and Coordinate Independent Convolutional Networks: A Gauge Field Theory of Neural Networks (Progress in Data Science)
Weiler, Maurice; Forré, Patrick; Verlinde, Erik; Welling, Max
- Couverture rigide
Vendeur : BOOKWEST, Phoenix, AZ, Etats-UnisBOOKWEST
Contacter le vendeurVendeur avec une évaluation de 4 étoilesEtat: Neuf
EUR 115,54
EUR 4,31 expéditionExpédition nationale : Etats-UnisQuantité disponible : 1 disponible(s)
Hardcover. Etat : New. US SELLER SHIPS FROM USA.
- Couverture rigide
Vendeur : GreatBookPrices, Columbia, MD, Etats-UnisGreatBookPrices
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 185,18
EUR 2,28 expéditionExpédition nationale : Etats-UnisQuantité disponible : Plus de 20 disponibles
Etat : New.
Equivariant and Coordinate Independent Convolutional Networks: A Gauge Field Theory of Neural Networks (Progress in Data Science)
Weiler, Maurice; Forré, Patrick; Verlinde, Erik; Welling, Max
- Couverture rigide
Vendeur : California Books, Miami, FL, Etats-UnisCalifornia Books
Contacter le vendeurVendeur avec une évaluation de 4 étoilesEtat: Neuf
EUR 187,54
Frais de port gratuitsExpédition nationale : Etats-UnisQuantité disponible : Plus de 20 disponibles
Etat : New.
- Couverture rigide
Vendeur : PBShop.store US, Wood Dale, IL, Etats-UnisPBShop.store US
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 193,20
Frais de port gratuitsExpédition nationale : Etats-UnisQuantité disponible : 15 disponible(s)
HRD. Etat : New. New Book. Shipped from UK. Established seller since 2000.
- Couverture rigide
Vendeur : PBShop.store UK, Fairford, GLOS, Royaume-UniPBShop.store UK
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 186,82
EUR 6,86 expéditionExpédition depuis Royaume-Uni vers Etats-UnisQuantité disponible : 15 disponible(s)
HRD. Etat : New. New Book. Shipped from UK. Established seller since 2000.
- Couverture rigide
Vendeur : GreatBookPrices, Columbia, MD, Etats-UnisGreatBookPrices
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Occasion - Comme neuf
EUR 198,24
EUR 2,28 expéditionExpédition nationale : Etats-UnisQuantité disponible : Plus de 20 disponibles
Etat : As New. Unread book in perfect condition.
- Couverture rigide
Vendeur : GreatBookPricesUK, Woodford Green, Royaume-UniGreatBookPricesUK
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 186,81
EUR 17,53 expéditionExpédition depuis Royaume-Uni vers Etats-UnisQuantité disponible : Plus de 20 disponibles
Etat : New.
Langue : anglais
Edité par World Scientific Publishing Co Pte Ltd, SG, 2026
- Couverture rigide
Vendeur : Rarewaves.com USA, London, LONDO, Royaume-UniRarewaves.com USA
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 218,70
Frais de port gratuitsExpédition depuis Royaume-Uni vers Etats-UnisQuantité disponible : 15 disponible(s)
Hardback. Etat : New. What is the appropriate geometric structure for neural networks that process spatial signals on Euclidean spaces or more general manifolds? This question takes us on a journey which leads to a gauge field theory of convolutional networks.Feature vector fields: The spatial signals we are interested in are fi…elds of feature vectors. Feature fields allow to describe data like images, audio, videos, point clouds, or tensor fields, such as fluid flows and electromagnetic fields.Equivariant networks commute with actions of some symmetry group on their feature spaces. The relevant group actions in this work are geometric transformations of feature fields, like translations, rotations, or reflections of images. Equivariant models generalize everything they learn over the considered group of transformations. This property makes them significantly more data efficient, interpretable, and robust in comparison to non-equivariant models.Convolutional Neural Networks (CNNs) are the most common network architecture for processing feature fields. Conventional CNNs operate on Euclidean spaces and are translation equivariant, i.e. position independent. This work explains how to extend CNNs to be equivariant under more general symmetries of space.Coordinate independence: Manifolds are in general not equipped with a canonical choice of coordinates. Feature fields and neural network layers are hence required to be coordinate independent, that is, expressible relative to different frames of reference. The ambiguity of local frames represents the gauge freedom of our neural field theory. We show that the demand for coordinate independence requires CNNs to be equivariant under local gauge transformations.To offer an easy entry, the first part of this work focuses on the representation theory of equivariant convolutional networks on Euclidean spaces. The insights gained in the Euclidean setting are subsequently leveraged to develop the full gauge theory of coordinate independent CNNs on Riemannian manifolds. In the last part, we turn to a discussion of practical applications on specific manifolds. A comprehensive literature review demonstrates the generality of our theory by showing for more than 100 models from the literature how they can be understood as specific instantiations of "Equivariant and Coordinate Independent CNNs".
- Couverture rigide
Vendeur : GreatBookPricesUK, Woodford Green, Royaume-UniGreatBookPricesUK
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Occasion - Comme neuf
EUR 204,76
EUR 17,53 expéditionExpédition depuis Royaume-Uni vers Etats-UnisQuantité disponible : Plus de 20 disponibles
Etat : As New. Unread book in perfect condition.
Langue : anglais
Edité par World Scientific Publishing Co Pte Ltd, Singapore, 2026
- Couverture rigide
Vendeur : Grand Eagle Retail, Bensenville, IL, Etats-UnisGrand Eagle Retail
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 229,50
Frais de port gratuitsExpédition nationale : Etats-UnisQuantité disponible : 1 disponible(s)
Hardcover. Etat : new. Hardcover. What is the appropriate geometric structure for neural networks that process spatial signals on Euclidean spaces or more general manifolds? This question takes us on a journey which leads to a gauge field theory of convolutional networks.Feature vector fields: The spatial signals we are interest…ed in are fields of feature vectors. Feature fields allow to describe data like images, audio, videos, point clouds, or tensor fields, such as fluid flows and electromagnetic fields.Equivariant networks commute with actions of some symmetry group on their feature spaces. The relevant group actions in this work are geometric transformations of feature fields, like translations, rotations, or reflections of images. Equivariant models generalize everything they learn over the considered group of transformations. This property makes them significantly more data efficient, interpretable, and robust in comparison to non-equivariant models.Convolutional Neural Networks (CNNs) are the most common network architecture for processing feature fields. Conventional CNNs operate on Euclidean spaces and are translation equivariant, i.e. position independent. This work explains how to extend CNNs to be equivariant under more general symmetries of space.Coordinate independence: Manifolds are in general not equipped with a canonical choice of coordinates. Feature fields and neural network layers are hence required to be coordinate independent, that is, expressible relative to different frames of reference. The ambiguity of local frames represents the gauge freedom of our neural field theory. We show that the demand for coordinate independence requires CNNs to be equivariant under local gauge transformations.To offer an easy entry, the first part of this work focuses on the representation theory of equivariant convolutional networks on Euclidean spaces. The insights gained in the Euclidean setting are subsequently leveraged to develop the full gauge theory of coordinate independent CNNs on Riemannian manifolds. In the last part, we turn to a discussion of practical applications on specific manifolds. A comprehensive literature review demonstrates the generality of our theory by showing for more than 100 models from the literature how they can be understood as specific instantiations of "Equivariant and Coordinate Independent CNNs". Shipping may be from multiple locations in the US or from the UK, depending on stock availability.
Equivariant and Coordinate Independent Convolutional Networks: A Gauge Field Theory of Neural Networks: 1 (Progress In Data Science)
Forre, Patrick (Author)/ Verlinde, Erik (Author)/ Weiler, Maurice (Author)/ Welling, Max (Author)
- Couverture rigide
Vendeur : Revaluation Books, Exeter, Royaume-UniRevaluation Books
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 249,51
EUR 14,60 expéditionExpédition depuis Royaume-Uni vers Etats-UnisQuantité disponible : 2 disponible(s)
Hardcover. Etat : Brand New. 592 pages. 2.36x0.85x9.00 inches. In Stock.
Langue : anglais
Edité par World Scientific Publishing Co Pte Ltd, SG, 2026
- Couverture rigide
Vendeur : Rarewaves.com UK, London, Royaume-UniRarewaves.com UK
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 214,44
EUR 75,94 expéditionExpédition depuis Royaume-Uni vers Etats-UnisQuantité disponible : 15 disponible(s)
Hardback. Etat : New. What is the appropriate geometric structure for neural networks that process spatial signals on Euclidean spaces or more general manifolds? This question takes us on a journey which leads to a gauge field theory of convolutional networks.Feature vector fields: The spatial signals we are interested in are fi…elds of feature vectors. Feature fields allow to describe data like images, audio, videos, point clouds, or tensor fields, such as fluid flows and electromagnetic fields.Equivariant networks commute with actions of some symmetry group on their feature spaces. The relevant group actions in this work are geometric transformations of feature fields, like translations, rotations, or reflections of images. Equivariant models generalize everything they learn over the considered group of transformations. This property makes them significantly more data efficient, interpretable, and robust in comparison to non-equivariant models.Convolutional Neural Networks (CNNs) are the most common network architecture for processing feature fields. Conventional CNNs operate on Euclidean spaces and are translation equivariant, i.e. position independent. This work explains how to extend CNNs to be equivariant under more general symmetries of space.Coordinate independence: Manifolds are in general not equipped with a canonical choice of coordinates. Feature fields and neural network layers are hence required to be coordinate independent, that is, expressible relative to different frames of reference. The ambiguity of local frames represents the gauge freedom of our neural field theory. We show that the demand for coordinate independence requires CNNs to be equivariant under local gauge transformations.To offer an easy entry, the first part of this work focuses on the representation theory of equivariant convolutional networks on Euclidean spaces. The insights gained in the Euclidean setting are subsequently leveraged to develop the full gauge theory of coordinate independent CNNs on Riemannian manifolds. In the last part, we turn to a discussion of practical applications on specific manifolds. A comprehensive literature review demonstrates the generality of our theory by showing for more than 100 models from the literature how they can be understood as specific instantiations of "Equivariant and Coordinate Independent CNNs".
Langue : anglais
Edité par World Scientific Publishing Co Pte Ltd, Singapore, 2026
- Couverture rigide
Vendeur : AussieBookSeller, Truganina, VIC, AustralieAussieBookSeller
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 345,92
EUR 31,93 expéditionExpédition depuis Australie vers Etats-UnisQuantité disponible : 1 disponible(s)
Hardcover. Etat : new. Hardcover. What is the appropriate geometric structure for neural networks that process spatial signals on Euclidean spaces or more general manifolds? This question takes us on a journey which leads to a gauge field theory of convolutional networks.Feature vector fields: The spatial signals we are interest…ed in are fields of feature vectors. Feature fields allow to describe data like images, audio, videos, point clouds, or tensor fields, such as fluid flows and electromagnetic fields.Equivariant networks commute with actions of some symmetry group on their feature spaces. The relevant group actions in this work are geometric transformations of feature fields, like translations, rotations, or reflections of images. Equivariant models generalize everything they learn over the considered group of transformations. This property makes them significantly more data efficient, interpretable, and robust in comparison to non-equivariant models.Convolutional Neural Networks (CNNs) are the most common network architecture for processing feature fields. Conventional CNNs operate on Euclidean spaces and are translation equivariant, i.e. position independent. This work explains how to extend CNNs to be equivariant under more general symmetries of space.Coordinate independence: Manifolds are in general not equipped with a canonical choice of coordinates. Feature fields and neural network layers are hence required to be coordinate independent, that is, expressible relative to different frames of reference. The ambiguity of local frames represents the gauge freedom of our neural field theory. We show that the demand for coordinate independence requires CNNs to be equivariant under local gauge transformations.To offer an easy entry, the first part of this work focuses on the representation theory of equivariant convolutional networks on Euclidean spaces. The insights gained in the Euclidean setting are subsequently leveraged to develop the full gauge theory of coordinate independent CNNs on Riemannian manifolds. In the last part, we turn to a discussion of practical applications on specific manifolds. A comprehensive literature review demonstrates the generality of our theory by showing for more than 100 models from the literature how they can be understood as specific instantiations of 'Equivariant and Coordinate Independent CNNs'. Shipping may be from our Sydney, NSW warehouse or from our UK or US warehouse, depending on stock availability.
Langue : anglais
Edité par World Scientific Publishing Co Pte Ltd, Singapore, 2026
- Couverture rigide
- impression à la demande
Vendeur : CitiRetail, Stevenage, Royaume-UniCitiRetail
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 223,22
EUR 43,23 expéditionExpédition depuis Royaume-Uni vers Etats-UnisQuantité disponible : 1 disponible(s)
Hardcover. Etat : new. Hardcover. What is the appropriate geometric structure for neural networks that process spatial signals on Euclidean spaces or more general manifolds? This question takes us on a journey which leads to a gauge field theory of convolutional networks.Feature vector fields: The spatial signals we are interest…ed in are fields of feature vectors. Feature fields allow to describe data like images, audio, videos, point clouds, or tensor fields, such as fluid flows and electromagnetic fields.Equivariant networks commute with actions of some symmetry group on their feature spaces. The relevant group actions in this work are geometric transformations of feature fields, like translations, rotations, or reflections of images. Equivariant models generalize everything they learn over the considered group of transformations. This property makes them significantly more data efficient, interpretable, and robust in comparison to non-equivariant models.Convolutional Neural Networks (CNNs) are the most common network architecture for processing feature fields. Conventional CNNs operate on Euclidean spaces and are translation equivariant, i.e. position independent. This work explains how to extend CNNs to be equivariant under more general symmetries of space.Coordinate independence: Manifolds are in general not equipped with a canonical choice of coordinates. Feature fields and neural network layers are hence required to be coordinate independent, that is, expressible relative to different frames of reference. The ambiguity of local frames represents the gauge freedom of our neural field theory. We show that the demand for coordinate independence requires CNNs to be equivariant under local gauge transformations.To offer an easy entry, the first part of this work focuses on the representation theory of equivariant convolutional networks on Euclidean spaces. The insights gained in the Euclidean setting are subsequently leveraged to develop the full gauge theory of coordinate independent CNNs on Riemannian manifolds. In the last part, we turn to a discussion of practical applications on specific manifolds. A comprehensive literature review demonstrates the generality of our theory by showing for more than 100 models from the literature how they can be understood as specific instantiations of 'Equivariant and Coordinate Independent CNNs'. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.
- Couverture rigide
- impression à la demande
Vendeur : AHA-BUCH GmbH, Einbeck, AllemagneAHA-BUCH GmbH
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 256,85
EUR 30,50 expéditionExpédition depuis Allemagne vers Etats-UnisQuantité disponible : 2 disponible(s)
Buch. Etat : Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - What is the appropriate geometric structure for neural networks that process spatial signals on Euclidean spaces or more general manifolds This question takes us on a journey which leads to a gauge field theory of convolutional networks.Feature vec…tor fields: The spatial signals we are interested in are fields of feature vectors. Feature fields allow to describe data like images, audio, videos, point clouds, or tensor fields, such as fluid flows and electromagnetic fields.Equivariant networks commute with actions of some symmetry group on their feature spaces. The relevant group actions in this work are geometric transformations of feature fields, like translations, rotations, or reflections of images. Equivariant models generalize everything they learn over the considered group of transformations. This property makes them significantly more data efficient, interpretable, and robust in comparison to non-equivariant models.Convolutional Neural Networks (CNNs) are the most common network architecture for processing feature fields. Conventional CNNs operate on Euclidean spaces and are translation equivariant, i.e. position independent. This work explains how to extend CNNs to be equivariant under more general symmetries of space.Coordinate independence: Manifolds are in general not equipped with a canonical choice of coordinates. Feature fields and neural network layers are hence required to be coordinate independent, that is, expressible relative to different frames of reference. The ambiguity of local frames represents the gauge freedom of our neural field theory. We show that the demand for coordinate independence requires CNNs to be equivariant under local gauge transformations.
- Couverture rigide
- impression à la demande
Vendeur : preigu, Osnabrück, Allemagnepreigu
Contacter le vendeurVendeur avec une évaluation de 5 étoilesEtat: Neuf
EUR 235,00
EUR 70,00 expéditionExpédition depuis Allemagne vers Etats-UnisQuantité disponible : 5 disponible(s)
Buch. Etat : Neu. EQUIVARIANT & COORDINATE INDEPENDENT CONVOLUTIONAL NETWORKS | Weiler Maurice | Buch | PROGRESS IN DATA SCIENCE | Englisch | 2026 | World Scientific | EAN 9789819806621 | Verantwortliche Person für die EU: Libri GmbH, Europaallee 1, 36244 Bad Hersfeld, gpsr[at]libri[dot]de | Anbieter: preigu Print on Demand.
