Accelerators for Convolutional Neural Networks

• Autore: Munir Arslan
• Pubblicazione: Newark : , : John Wiley & Sons, Incorporated, , 2023; ©2024
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (307 pages)
• Disciplina: 006.32
• Soggetto topico: Neural networks (Computer science); Computer architecture
• Altri autori: KongJoonho QureshiMahmood Azhar
• 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.
• Titolo autorizzato: Accelerators for Convolutional Neural Networks
• ISBN: 9781394171897; 9781394171910
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9911019510703321
• Lo trovi qui: Univ. Federico II