1.

Record Nr.

UNINA9910452112103321

Titolo

Sediment dredging at Superfund megasites [[electronic resource] ] : assessing the effectiveness / / Committee on Sediment Dredging at Superfund Megasites, Board on Environmental Studies and Toxicology, Division on Earth and Life Studies, National Research Council of the National Academies

Pubbl/distr/stampa

Washington, D.C., : National Academies Press, c2007

ISBN

1-281-10997-5

9786611109974

0-309-10978-7

Descrizione fisica

1 online resource (316 p.)

Soggetti

Dredging - Environmental aspects

Dredging spoil

Contaminated sediments - Environmental aspects

Hazardous waste site remediation - United States

Electronic books.

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Note generali

Bibliographic Level Mode of Issuance: Monograph

Nota di bibliografia

Includes bibliographical references.



2.

Record Nr.

UNINA9910739463803321

Autore

Lee Juhyoung

Titolo

Deep Reinforcement Learning Processor Design for Mobile Applications / / by Juhyoung Lee, Hoi-Jun Yoo

Pubbl/distr/stampa

Cham : , : Springer Nature Switzerland : , : Imprint : Springer, , 2023

ISBN

9783031367939

3031367936

Edizione

[1st ed. 2023.]

Descrizione fisica

1 online resource (105 pages)

Altri autori (Persone)

YooHoi-Jun

Disciplina

621.38456

Soggetti

Electronic circuits

Embedded computer systems

Microprocessors

Computer architecture

Electronic Circuits and Systems

Embedded Systems

Processor Architectures

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Nota di contenuto

Introduction -- Background of Deep Reinforcement Learning -- Group-Sparse Training Algorithm for Accelerating Deep Reinforcement Learning -- An Energy-Efficient Deep Reinforcement Learning Processor Design -- Low-power Autonomous Adaptation System with Deep Reinforcement Learning -- Low-power Autonomous Adaptation System with Deep Reinforcement Learning -- Exponent-Computing-in-Memory for DNN Training Processor with Energy-Efficient Heterogeneous Floating-point Computing Architecture.

Sommario/riassunto

This book discusses the acceleration of deep reinforcement learning (DRL), which may be the next step in the burst success of artificial intelligence (AI). The authors address acceleration systems which enable DRL on area-limited & battery-limited mobile devices. Methods are described that enable DRL optimization at the algorithm-, architecture-, and circuit-levels of abstraction. Enables deep reinforcement learning (DRL) optimization at algorithm-, architecture-, and circuit-levels of abstraction; Includes methodologies that can



reduce the high cost of DRL; Uses analysis of computational workload characteristics of DRL in the context of acceleration.