| Description |
1 online resource (xiv, 477 pages) : illustrations (some color) |
| Contents |
Intro -- Preface -- Acknowledgments -- Contents -- Part I Efficient Software Design for Embedded Machine Learning -- Machine Learning Model Compression for Efficient Indoor Localization on Embedded Platforms -- 1 Introduction -- 2 Background and Related Work -- 3 CHISEL Framework -- 3.1 Data Preprocessing and Augmentation -- 3.2 Network Architecture -- 3.3 Model Compression -- 4 Experiments -- 4.1 Evaluation on UJIIndoorLoc Dataset -- 4.2 Evaluation on Compression-Aware Training -- 5 Conclusion -- References -- A Design Methodology for Energy-Efficient Embedded Spiking Neural Networks |
|
1 Introduction -- 1.1 Overview -- 1.2 Design Constraints for Embedded SNNs -- 2 Preliminaries -- 2.1 Spiking Neural Networks (SNNs) -- 2.2 Spike-Timing-Dependent Plasticity (STDP) -- 3 A Design Methodology for Embedded SNNs -- 3.1 Overview -- 3.2 Reduction of SNN Operations -- 3.3 Learning Enhancements -- 3.4 Weight Quantization -- 3.5 Evaluation of Memory and Energy Requirements -- 3.6 Employment of Approximate DRAM -- 4 Experimental Evaluations -- 4.1 Classification Accuracy -- 4.2 Reduction of Memory Requirement -- 4.3 Improvement of Energy Efficiency -- 4.4 Impact of Approximate DRAM |
|
5 Conclusion -- References -- Compilation and Optimizations for Efficient Machine Learning on Embedded Systems -- 1 Introduction -- 2 Background and Related Works -- 2.1 Efficient DNN Designs -- 2.2 Efficient Accelerator Designs and DNN Mapping Methods -- 2.3 Efficient Co-Design Optimization -- 3 Efficient Machine Learning Model Designs -- 3.1 The ELB-NN -- 3.1.1 Hybrid Quantization Scheme -- 3.1.2 Hardware Accelerator for ELB-NN -- 3.2 The VecQ -- 3.2.1 Quantization with Vector Loss -- 3.2.2 Framework Integration -- 4 Efficient Accelerator Design and Workload Mapping -- 4.1 DNNBuilder |
|
4.1.1 An End-to-end Automation Flow -- 4.1.2 Architecture Novelties -- 4.1.3 State-of-the-art Performance -- 4.2 PyLog: A Python-Based FPGA Programming Flow -- 4.2.1 PyLog Flow Overview -- 4.2.2 PyLog Features -- 4.2.3 PyLog Evaluation Results -- 5 Efficient Optimizations -- 5.1 Overview of Hardware-aware Neural Architecture Search (NAS) -- 5.2 HW-Aware NAS Formulation -- 5.3 FPGA/DNN Co-Design -- 5.3.1 The Key to Co-Design: Bundle -- 5.3.2 Progressively Reducing Search Space -- 5.3.3 Evaluation Results -- 5.4 EDD: Efficient Differential DNN Architecture Search -- 5.4.1 Fused Co-Design Space |
|
5.4.2 Differentiable Performance and Resource Formulation -- 5.4.3 State-of-the-art Results -- 6 Conclusion -- References -- A Pedestrian Detection Case Study for a Traffic Light Controller -- 1 Introduction -- 2 Related Work -- 2.1 Neural Networks for Pedestrian Detection -- 2.2 Pedestrian Detection on Embedded Systems -- 2.3 Quantization -- 3 Pedestrian Detection Use Case -- 4 Results -- 4.1 Experimentation Setup -- 4.2 No Constraints -- 4.3 Cost Constraints -- 4.4 Cost, Latency, and Precision Constraints -- 4.5 Effect of Resolution and Quantization -- 5 Conclusion -- References |
| Summary |
This book presents recent advances towards the goal of enabling efficient implementation of machine learning models on resource-constrained systems, covering different application domains. The focus is on presenting interesting and new use cases of applying machine learning to innovative application domains, exploring the efficient hardware design of efficient machine learning accelerators, memory optimization techniques, illustrating model compression and neural architecture search techniques for energy-efficient and fast execution on resource-constrained hardware platforms, and understanding hardware-software codesign techniques for achieving even greater energy, reliability, and performance benefits. Discusses efficient implementation of machine learning in embedded, CPS, IoT, and edge computing; Offers comprehensive coverage of hardware design, software design, and hardware/software co-design and co-optimization; Describes real applications to demonstrate how embedded, CPS, IoT, and edge applications benefit from machine learning |
| Notes |
Includes index |
|
Online resource; title from PDF title page (SpringerLink, viewed October 20, 2023) |
| Subject |
Cooperating objects (Computer systems)
|
|
Machine learning.
|
|
Cooperating objects (Computer systems)
|
|
Machine learning
|
| Form |
Electronic book
|
| Author |
Pasricha, Sudeep, editor.
|
|
Shafique, Muhammad, editor.
|
| ISBN |
9783031399329 |
|
3031399323 |
|
