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.
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 costiDa: moluna, Greven, Germania
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
Quantità: 1 disponibili
Da: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Germania
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
Quantità: 2 disponibili
Da: Ria Christie Collections, Uxbridge, Regno Unito
Condizione: New. In. Codice articolo ria9789811682322_new
Quantità: Più di 20 disponibili
Da: buchversandmimpf2000, Emtmannsberg, BAYE, Germania
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
Quantità: 2 disponibili
Da: AHA-BUCH GmbH, Einbeck, Germania
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
Quantità: 1 disponibili
Da: California Books, Miami, FL, U.S.A.
Condizione: New. Codice articolo I-9789811682322
Quantità: Più di 20 disponibili
Da: CitiRetail, Stevenage, Regno Unito
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
Quantità: 1 disponibili
Da: Books Puddle, New York, NY, U.S.A.
Condizione: New. 1st ed. 2022 edition NO-PA16APR2015-KAP. Codice articolo 26396346908
Quantità: 4 disponibili
Da: AussieBookSeller, Truganina, VIC, Australia
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
Quantità: 1 disponibili
Da: Majestic Books, Hounslow, Regno Unito
Condizione: New. Print on Demand. Codice articolo 401111491
Quantità: 4 disponibili