Articoli correlati a Foundations of Deep Learning

Foundations of Deep Learning - Rilegato

 
9789811682322: Foundations of Deep Learning

Sinossi

Deep learning has significantly reshaped a variety of technologies, such as image processing, natural language processing, and audio processing. The excellent generalizability of deep learning is like a “cloud” to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. This irreconciliation considerably undermines the confidence of deploying deep learning to security-critical areas, including autonomous vehicles and medical diagnosis, where small algorithmic mistakes can lead to fatal disasters. This book seeks to explaining the excellent generalizability, including generalization analysis via the size-independent complexity measures, the role of optimization in understanding the generalizability, and the relationship between generalizability and ethical/security issues. 

The efforts to understand the excellent generalizability are following two major paths: (1) developing size-independent complexity measures, which can evaluate the “effective” hypothesis complexity that can be learned, instead of the whole hypothesis space; and (2) modelling the learned hypothesis through stochastic gradient methods, the dominant optimizers in deep learning, via stochastic differential functions and the geometry of the associated loss functions. Related works discover that over-parameterization surprisingly bring many good properties to the loss functions. Rising concerns of deep learning are seen on the ethical and security issues, including privacy preservation and adversarial robustness. Related works also reveal an interplay between them and generalizability: a good generalizability usually means a good privacy-preserving ability; and more robust algorithms might have a worse generalizability.

 We expect readers can have a big picture of the current knowledge in deep learning theory, understand how the deep learning theory can guide new algorithm designing, and identify future research directions. Readers need knowledge of calculus, linear algebra, probability, statistics, and statistical learning theory.

Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.

Informazioni sull?autore


Dalla quarta di copertina

Deep learning has significantly reshaped a variety of technologies, such as image processing, natural language processing, and audio processing. The excellent generalizability of deep learning is like a “cloud” to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. This irreconciliation considerably undermines the confidence of deploying deep learning to security-critical areas, including autonomous vehicles and medical diagnosis, where small algorithmic mistakes can lead to fatal disasters. This book seeks to explaining the excellent generalizability, including generalization analysis via the size-independent complexity measures, the role of optimization in understanding the generalizability, and the relationship between generalizability and ethical/security issues. 

The efforts to understand the excellent generalizability are following two major paths: (1) developing size-independent complexity measures, which can evaluate the “effective” hypothesis complexity that can be learned, instead of the whole hypothesis space; and (2) modelling the learned hypothesis through stochastic gradient methods, the dominant optimizers in deep learning, via stochastic differential functions and the geometry of the associated loss functions. Related works discover that over-parameterization surprisingly bring many good properties to the loss functions. Rising concerns of deep learning are seen on the ethical and security issues, including privacy preservation and adversarial robustness. Related works also reveal an interplay between them and generalizability: a good generalizability usually means a good privacy-preserving ability; and more robust algorithms might have a worse generalizability.

 

We expect readers can have a big picture of the current knowledge in deep learning theory, understand how the deep learning theory can guide new algorithm designing, and identify future research directions. Readers need knowledge of calculus, linear algebra, probability, statistics, and statistical learning theory.

Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.

EUR 9,70 per la spedizione da Germania a Italia

Destinazione, tempi e costi

Risultati della ricerca per Foundations of Deep Learning

Immagini fornite dal venditore

Fengxiang He|Dacheng Tao
Editore: Springer Nature Singapore, 2024
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato

Da: moluna, Greven, Germania

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Condizione: New. The first comprehensive overview book on the foundations of deep learningWritten by leading experts in the fieldExplicates excellent generalizability of deep learning, including generalization analysisDeep learning has si. Codice articolo 521847426

Contatta il venditore

Compra nuovo

EUR 123,53
Convertire valuta
Spese di spedizione: EUR 9,70
Da: Germania a: Italia
Destinazione, tempi e costi

Quantità: 1 disponibili

Aggiungi al carrello

Immagini fornite dal venditore

Fengxiang He
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato
Print on Demand

Da: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Germania

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Buch. Condizione: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Deep learning has significantly reshaped a variety of technologies, such as image processing, natural language processing, and audio processing. The excellent generalizability of deep learning is like a 'cloud' to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. This irreconciliation considerably undermines the confidence of deploying deep learning to security-critical areas, including autonomous vehicles and medical diagnosis, where small algorithmic mistakes can lead to fatal disasters. This book seeks to explaining the excellent generalizability, including generalization analysis via the size-independent complexity measures, the role of optimization in understanding the generalizability, and the relationship between generalizability and ethical/security issues.The efforts to understand the excellent generalizability are following two major paths: (1) developing size-independent complexity measures, which can evaluate the 'effective' hypothesis complexity that can be learned, instead of the whole hypothesis space; and (2) modelling the learned hypothesis through stochastic gradient methods, the dominant optimizers in deep learning, via stochastic differential functions and the geometry of the associated loss functions. Related works discover that over-parameterization surprisingly bring many good properties to the loss functions. Rising concerns of deep learning are seen on the ethical and security issues, including privacy preservation and adversarial robustness. Related works also reveal an interplay between them and generalizability: a good generalizability usually means a good privacy-preserving ability; and more robust algorithms might have a worse generalizability.We expect readers can have a big picture of the current knowledge in deep learning theory, understand how the deep learning theory can guide new algorithm designing, and identify future research directions. Readers need knowledge of calculus, linear algebra, probability, statistics, and statistical learning theory. 284 pp. Englisch. Codice articolo 9789811682322

Contatta il venditore

Compra nuovo

EUR 149,79
Convertire valuta
Spese di spedizione: EUR 11,00
Da: Germania a: Italia
Destinazione, tempi e costi

Quantità: 2 disponibili

Aggiungi al carrello

Foto dell'editore

He, Fengxiang; Tao, Dacheng
Editore: Springer, 2025
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato

Da: Ria Christie Collections, Uxbridge, Regno Unito

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Condizione: New. In. Codice articolo ria9789811682322_new

Contatta il venditore

Compra nuovo

EUR 152,47
Convertire valuta
Spese di spedizione: EUR 10,33
Da: Regno Unito a: Italia
Destinazione, tempi e costi

Quantità: Più di 20 disponibili

Aggiungi al carrello

Immagini fornite dal venditore

Dacheng Tao
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato

Da: buchversandmimpf2000, Emtmannsberg, BAYE, Germania

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Buch. Condizione: Neu. Neuware -Deep learning has significantly reshaped a variety of technologies, such as image processing, natural language processing, and audio processing. The excellent generalizability of deep learning is like a 'cloud' to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. This irreconciliation considerably undermines the confidence of deploying deep learning to security-critical areas, including autonomous vehicles and medical diagnosis, where small algorithmic mistakes can lead to fatal disasters. This book seeks to explaining the excellent generalizability, including generalization analysis via the size-independent complexity measures, the role of optimization in understanding the generalizability, and the relationship between generalizability and ethical/security issues.Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg 308 pp. Englisch. Codice articolo 9789811682322

Contatta il venditore

Compra nuovo

EUR 149,79
Convertire valuta
Spese di spedizione: EUR 15,00
Da: Germania a: Italia
Destinazione, tempi e costi

Quantità: 2 disponibili

Aggiungi al carrello

Immagini fornite dal venditore

Dacheng Tao
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato

Da: AHA-BUCH GmbH, Einbeck, Germania

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Buch. Condizione: Neu. Druck auf Anfrage Neuware - Printed after ordering - Deep learning has significantly reshaped a variety of technologies, such as image processing, natural language processing, and audio processing. The excellent generalizability of deep learning is like a 'cloud' to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. This irreconciliation considerably undermines the confidence of deploying deep learning to security-critical areas, including autonomous vehicles and medical diagnosis, where small algorithmic mistakes can lead to fatal disasters. This book seeks to explaining the excellent generalizability, including generalization analysis via the size-independent complexity measures, the role of optimization in understanding the generalizability, and the relationship between generalizability and ethical/security issues.The efforts to understand the excellent generalizability are following two major paths: (1) developing size-independent complexity measures, which can evaluate the 'effective' hypothesis complexity that can be learned, instead of the whole hypothesis space; and (2) modelling the learned hypothesis through stochastic gradient methods, the dominant optimizers in deep learning, via stochastic differential functions and the geometry of the associated loss functions. Related works discover that over-parameterization surprisingly bring many good properties to the loss functions. Rising concerns of deep learning are seen on the ethical and security issues, including privacy preservation and adversarial robustness. Related works also reveal an interplay between them and generalizability: a good generalizability usually means a good privacy-preserving ability; and more robust algorithms might have a worse generalizability.We expect readers can have a big picture of the current knowledge in deep learning theory, understand how the deep learning theory can guide new algorithm designing, and identify future research directions. Readers need knowledge of calculus, linear algebra, probability, statistics, and statistical learning theory. Codice articolo 9789811682322

Contatta il venditore

Compra nuovo

EUR 151,07
Convertire valuta
Spese di spedizione: EUR 14,99
Da: Germania a: Italia
Destinazione, tempi e costi

Quantità: 1 disponibili

Aggiungi al carrello

Foto dell'editore

He, Fengxiang; Tao, Dacheng
Editore: Springer, 2025
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato

Da: California Books, Miami, FL, U.S.A.

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Condizione: New. Codice articolo I-9789811682322

Contatta il venditore

Compra nuovo

EUR 166,48
Convertire valuta
Spese di spedizione: EUR 7,66
Da: U.S.A. a: Italia
Destinazione, tempi e costi

Quantità: Più di 20 disponibili

Aggiungi al carrello

Foto dell'editore

Fengxiang He
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato

Da: CitiRetail, Stevenage, Regno Unito

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Hardcover. Condizione: new. Hardcover. Deep learning has significantly reshaped a variety of technologies, such as image processing, natural language processing, and audio processing. The excellent generalizability of deep learning is like a cloud to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. This irreconciliation considerably undermines the confidence of deploying deep learning to security-critical areas, including autonomous vehicles and medical diagnosis, where small algorithmic mistakes can lead to fatal disasters. This book seeks to explaining the excellent generalizability, including generalization analysis via the size-independent complexity measures, the role of optimization in understanding the generalizability, and the relationship between generalizability and ethical/security issues. The efforts to understand the excellent generalizability are following two major paths: (1) developing size-independent complexity measures, which can evaluate the effective hypothesis complexity that can be learned, instead of the whole hypothesis space; and (2) modelling the learned hypothesis through stochastic gradient methods, the dominant optimizers in deep learning, via stochastic differential functions and the geometry of the associated loss functions. Related works discover that over-parameterization surprisingly bring many good properties to the loss functions. Rising concerns of deep learning are seen on the ethical and security issues, including privacy preservation and adversarial robustness. Related works also reveal an interplay between them and generalizability: a good generalizability usually means a good privacy-preserving ability; and more robust algorithms might have a worse generalizability. We expect readers can have a big picture of the current knowledge in deep learning theory, understand how the deep learning theory can guide new algorithm designing, and identify future research directions. Readers need knowledge of calculus, linear algebra, probability, statistics, and statistical learning theory. The excellent generalizability of deep learning is like a cloud to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability. Codice articolo 9789811682322

Contatta il venditore

Compra nuovo

EUR 160,37
Convertire valuta
Spese di spedizione: EUR 34,48
Da: Regno Unito a: Italia
Destinazione, tempi e costi

Quantità: 1 disponibili

Aggiungi al carrello

Foto dell'editore

He, Fengxiang; Tao, Dacheng
Editore: Springer, 2025
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato

Da: Books Puddle, New York, NY, U.S.A.

Valutazione del venditore 4 su 5 stelle 4 stelle, Maggiori informazioni sulle valutazioni dei venditori

Condizione: New. 1st ed. 2022 edition NO-PA16APR2015-KAP. Codice articolo 26396346908

Contatta il venditore

Compra nuovo

EUR 202,30
Convertire valuta
Spese di spedizione: EUR 7,66
Da: U.S.A. a: Italia
Destinazione, tempi e costi

Quantità: 4 disponibili

Aggiungi al carrello

Foto dell'editore

Fengxiang He
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato

Da: AussieBookSeller, Truganina, VIC, Australia

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Hardcover. Condizione: new. Hardcover. Deep learning has significantly reshaped a variety of technologies, such as image processing, natural language processing, and audio processing. The excellent generalizability of deep learning is like a cloud to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. This irreconciliation considerably undermines the confidence of deploying deep learning to security-critical areas, including autonomous vehicles and medical diagnosis, where small algorithmic mistakes can lead to fatal disasters. This book seeks to explaining the excellent generalizability, including generalization analysis via the size-independent complexity measures, the role of optimization in understanding the generalizability, and the relationship between generalizability and ethical/security issues. The efforts to understand the excellent generalizability are following two major paths: (1) developing size-independent complexity measures, which can evaluate the effective hypothesis complexity that can be learned, instead of the whole hypothesis space; and (2) modelling the learned hypothesis through stochastic gradient methods, the dominant optimizers in deep learning, via stochastic differential functions and the geometry of the associated loss functions. Related works discover that over-parameterization surprisingly bring many good properties to the loss functions. Rising concerns of deep learning are seen on the ethical and security issues, including privacy preservation and adversarial robustness. Related works also reveal an interplay between them and generalizability: a good generalizability usually means a good privacy-preserving ability; and more robust algorithms might have a worse generalizability. We expect readers can have a big picture of the current knowledge in deep learning theory, understand how the deep learning theory can guide new algorithm designing, and identify future research directions. Readers need knowledge of calculus, linear algebra, probability, statistics, and statistical learning theory. The excellent generalizability of deep learning is like a cloud to conventional complexity-based learning theory: the over-parameterization of deep learning makes almost all existing tools vacuous. Shipping may be from our Sydney, NSW warehouse or from our UK or US warehouse, depending on stock availability. Codice articolo 9789811682322

Contatta il venditore

Compra nuovo

EUR 183,00
Convertire valuta
Spese di spedizione: EUR 31,48
Da: Australia a: Italia
Destinazione, tempi e costi

Quantità: 1 disponibili

Aggiungi al carrello

Foto dell'editore

He, Fengxiang; Tao, Dacheng
Editore: Springer, 2025
ISBN 10: 9811682321 ISBN 13: 9789811682322
Nuovo Rilegato
Print on Demand

Da: Majestic Books, Hounslow, Regno Unito

Valutazione del venditore 5 su 5 stelle 5 stelle, Maggiori informazioni sulle valutazioni dei venditori

Condizione: New. Print on Demand. Codice articolo 401111491

Contatta il venditore

Compra nuovo

EUR 213,09
Convertire valuta
Spese di spedizione: EUR 10,17
Da: Regno Unito a: Italia
Destinazione, tempi e costi

Quantità: 4 disponibili

Aggiungi al carrello

Vedi altre 3 copie di questo libro

Vedi tutti i risultati per questo libro