Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing

Bert Moons, Daniel Bankman, Marian Verhelst

  • Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing-preview-1
  • Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing-preview-2
  • Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing-preview-3
  • Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing-preview-4
  • Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing-preview-5
  • Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing-preview-6
Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing-preview-1

買這商品的人也買了...

商品描述

 

This book covers algorithmic and hardware implementation techniques to enable embedded deep learning. The authors describe synergetic design approaches on the application-, algorithmic-, computer architecture-, and circuit-level that will help in achieving the goal of reducing the computational cost of deep learning algorithms. The impact of these techniques is displayed in four silicon prototypes for embedded deep learning.

 

 

 

 

  • Gives a wide overview of a series of effective solutions for energy-efficient neural networks on battery constrained wearable devices;
  • Discusses the optimization of neural networks for embedded deployment on all levels of the design hierarchy – applications, algorithms, hardware architectures, and circuits – supported by real silicon prototypes;
  • Elaborates on how to design efficient Convolutional Neural Network processors, exploiting parallelism and data-reuse, sparse operations, and low-precision computations;
  • Supports the introduced theory and design concepts by four real silicon prototypes. The physical realization’s implementation and achieved performances are discussed elaborately to illustrated and highlight the introduced cross-layer design concepts.

 

商品描述(中文翻譯)

本書介紹了嵌入式深度學習的演算法和硬體實現技術。作者描述了應用、演算法、電腦架構和電路層面上的協同設計方法,以實現減少深度學習演算法計算成本的目標。這些技術的影響在四個嵌入式深度學習的矽原型中展示出來。

本書的主要內容包括:

- 提供了一系列針對電池受限可穿戴設備的節能神經網絡的有效解決方案的廣泛概述;
- 討論了在設計層次的各個層面上對神經網絡進行優化,包括應用、演算法、硬體架構和電路,並支持實際的矽原型;
- 詳細說明了如何設計高效的卷積神經網絡處理器,利用並行處理和數據重用、稀疏操作和低精度計算;
- 通過四個實際的矽原型來支持介紹的理論和設計概念。詳細討論了實際實現的實現和性能,以說明和突出介紹的跨層設計概念。