Energy Efficiency and Robustness of Advanced Machine Learning Architectures A Cross-Layer Approach

Machine Learning (ML) algorithms have shown a high level of accuracy, and applications are widely used in many systems and platforms. However, developing efficient ML-based systems requires addressing three problems: energy-efficiency, robustness, and techniques that typically focus on optimizing fo...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Marchisio, Alberto, Shafique, Muhammad
Format:	E-Book
Sprache:	Englisch
Veröffentlicht:	Milton CRC Press 2025 Taylor & Francis CRC Press LLC
Ausgabe:	1
Schriftenreihe:	Chapman & Hall/CRC Artificial Intelligence and Robotics Series
Schlagworte:	Artificial intelligence Automatic control engineering Classical mechanics Computer programming / software engineering Computer science Computer Technology Computing and Information Technology Cybersecurity Deep Learning Edge Computing Electrical engineering Electronics and communications engineering Electronics engineering Energy Energy technology and engineering Information technology: general topics Machine learning Mathematics and Science Neural Networks Neural networks and fuzzy systems Nonfiction Physics Processing Element Software Engineering Technical design Technology, Engineering, Agriculture, Industrial processes Technology: general issues TJFM1 Robotics AI Neural Networks Edge Computing Cybersecurity Processing Element Deep Learning
ISBN:	1032870133, 9781032855509, 9781032870137, 1032855509, 1040165036, 9781040165065, 9781040165034, 9781003530459, 1003530451, 1040165060
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Machine Learning (ML) algorithms have shown a high level of accuracy, and applications are widely used in many systems and platforms. However, developing efficient ML-based systems requires addressing three problems: energy-efficiency, robustness, and techniques that typically focus on optimizing for a single objective/have a limited set of goals. This book tackles these challenges by exploiting the unique features of advanced ML models and investigates cross-layer concepts and techniques to engage both hardware and software-level methods to build robust and energy-efficient architectures for these advanced ML networks. More specifically, this book improves the energy efficiency of complex models like CapsNets, through a specialized flow of hardware-level designs and software-level optimizations exploiting the application-driven knowledge of these systems and the error tolerance through approximations and quantization. This book also improves the robustness of ML models, in particular for SNNs executed on neuromorphic hardware, due to their inherent cost-effective features. This book integrates multiple optimization objectives into specialized frameworks for jointly optimizing the robustness and energy efficiency of these systems. This is an important resource for students and researchers of computer and electrical engineering who are interested in developing energy efficient and robust ML.
Bibliographie:	Electronic reproduction. Abingdon: Chapman and Hall/CRC, 2024. Requires the Libby app or a modern web browser.
ISBN:	1032870133 9781032855509 9781032870137 1032855509 1040165036 9781040165065 9781040165034 9781003530459 1003530451 1040165060
DOI:	10.1201/9781003530459