1.

Record Nr.

UNICASUBO3324332

Autore

Oliver, Annie

Titolo

Le biographique / Annie Oliver

Pubbl/distr/stampa

Paris, : Hatier, c2001

ISBN

221873608X

Descrizione fisica

159 p. ; 18 cm.

Collana

Profil ,  littérature , Profil litterature. Histoire litteraire ; 260-261

Lingua di pubblicazione

Francese

Formato

Materiale a stampa

Livello bibliografico

Monografia

2.

Record Nr.

UNINA9911019510703321

Autore

Munir Arslan

Titolo

Accelerators for Convolutional Neural Networks

Pubbl/distr/stampa

Newark : , : John Wiley & Sons, Incorporated, , 2023

©2024

ISBN

9781394171897

9781394171910

Edizione

[1st ed.]

Descrizione fisica

1 online resource (307 pages)

Altri autori (Persone)

KongJoonho

QureshiMahmood Azhar

Disciplina

006.32

Soggetti

Neural networks (Computer science)

Computer architecture

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Nota di contenuto

Cover -- Title Page -- Copyright -- Contents -- About the Authors -- Preface -- Part I Overview --   Chapter 1 Introduction --     1.1 History and Applications --     1.2 Pitfalls of High‐Accuracy DNNs/CNNs --      



1.2.1 Compute and Energy Bottleneck --       1.2.2 Sparsity Considerations --     1.3 Chapter Summary --   Chapter 2 Overview of Convolutional Neural Networks --     2.1 Deep Neural Network Architecture --     2.2 Convolutional Neural Network Architecture --       2.2.1 Data Preparation --       2.2.2 Building Blocks of CNNs --         2.2.2.1 Convolutional Layers --         2.2.2.2 Pooling Layers --         2.2.2.3 Fully Connected Layers --       2.2.3 Parameters of CNNs --       2.2.4 Hyperparameters of CNNs --         2.2.4.1 Hyperparameters Related to Network Structure --         2.2.4.2 Hyperparameters Related to Training --         2.2.4.3 Hyperparameter Tuning --     2.3 Popular CNN Models --       2.3.1 AlexNet --       2.3.2 VGGNet --       2.3.3 GoogleNet

Sommario/riassunto

This book provides an in-depth exploration of accelerators for convolutional neural networks (CNNs), a pivotal component in the field of artificial intelligence and computer vision. It covers the architecture of CNNs, compressive coding techniques, and the design of both dense and sparse CNN accelerators. The text discusses hardware and software co-design and scheduling strategies to optimize CNN performance. Aimed at students, researchers, and professionals in computer architecture and hardware design, the book serves as a comprehensive reference on the development and implementation of CNN accelerators.