Energy Efficiency and Robustness of Advanced Machine Learning Architectures

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...

Description complète

Enregistré dans:
Détails bibliographiques
Auteurs principaux: Marchisio, Alberto, Shafique, Muhammad
Format: Online
Langue:anglais
Publié: Taylor & Francis 2025
Sujets:
Accès en ligne:ONIX_20250310_9781040165034_9
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1869526947084632064
author Marchisio, Alberto
Shafique, Muhammad
author_browse Marchisio, Alberto
Shafique, Muhammad
author_facet Marchisio, Alberto
Shafique, Muhammad
author_sort Marchisio, Alberto
collection Directory of Open Access Books
description 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.
format Online
id doab-20.500.12854ir-157654
institution Directory of Open Access Books
language eng
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher Taylor & Francis
publisherStr Taylor & Francis
record_format ojs
spelling doab-20.500.12854ir-1576542025-07-29T21:06:29Z Energy Efficiency and Robustness of Advanced Machine Learning Architectures Marchisio, Alberto Shafique, Muhammad AI Cybersecurity Deep Learning Edge Computing Neural Networks Processing Element thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TJ Electronics and communications engineering::TJF Electronics engineering::TJFM Automatic control engineering::TJFM1 Robotics thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQN Neural networks and fuzzy systems thema EDItEUR::U Computing and Information Technology::UB Information technology: general topics thema EDItEUR::U Computing and Information Technology::UM Computer programming / software engineering::UMZ Software Engineering thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues::TBD Technical design thema EDItEUR::P Mathematics and Science::PH Physics::PHD Classical mechanics::PHDY Energy thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering 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. 2025-03-23T09:29:17Z 2025-03-23T09:29:17Z 2025-03-10T10:57:26Z 2025 book ONIX_20250310_9781040165034_9 https://library.oapen.org/handle/20.500.12657/99315 9781040165034 9781003530459 9781032855509 9781040165065 https://directory.doabooks.org/handle/20.500.12854/157654 eng Chapman & Hall/CRC Artificial Intelligence and Robotics Series open access image/jpeg image/jpeg image/jpeg Attribution-NonCommercial-NoDerivatives 4.0 International Attribution-NonCommercial-NoDerivatives 4.0 International Attribution-NonCommercial-NoDerivatives 4.0 International https://library.oapen.org/bitstream/20.500.12657/99315/1/9781040165034.pdf https://library.oapen.org/bitstream/20.500.12657/99315/12/9781040165034.pdf https://library.oapen.org/bitstream/20.500.12657/99315/12/9781040165034.pdf Taylor & Francis Chapman and Hall/CRC 10.1201/9781003530459 10.1201/9781003530459 fa69b019-f4ee-4979-8d42-c6b6c476b5f0 Knowledge Unlatched b818ba9d-2dd9-4fd7-a364-7f305aef7ee9 9781040165034 9781003530459 9781032855509 9781040165065 Knowledge Unlatched (KU) Chapman and Hall/CRC 360 [...] open access
spellingShingle AI
Cybersecurity
Deep Learning
Edge Computing
Neural Networks
Processing Element
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TJ Electronics and communications engineering::TJF Electronics engineering::TJFM Automatic control engineering::TJFM1 Robotics
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQN Neural networks and fuzzy systems
thema EDItEUR::U Computing and Information Technology::UB Information technology: general topics
thema EDItEUR::U Computing and Information Technology::UM Computer programming / software engineering::UMZ Software Engineering
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues::TBD Technical design
thema EDItEUR::P Mathematics and Science::PH Physics::PHD Classical mechanics::PHDY Energy
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
Marchisio, Alberto
Shafique, Muhammad
Energy Efficiency and Robustness of Advanced Machine Learning Architectures
title Energy Efficiency and Robustness of Advanced Machine Learning Architectures
title_full Energy Efficiency and Robustness of Advanced Machine Learning Architectures
title_fullStr Energy Efficiency and Robustness of Advanced Machine Learning Architectures
title_full_unstemmed Energy Efficiency and Robustness of Advanced Machine Learning Architectures
title_short Energy Efficiency and Robustness of Advanced Machine Learning Architectures
title_sort energy efficiency and robustness of advanced machine learning architectures
topic AI
Cybersecurity
Deep Learning
Edge Computing
Neural Networks
Processing Element
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TJ Electronics and communications engineering::TJF Electronics engineering::TJFM Automatic control engineering::TJFM1 Robotics
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQN Neural networks and fuzzy systems
thema EDItEUR::U Computing and Information Technology::UB Information technology: general topics
thema EDItEUR::U Computing and Information Technology::UM Computer programming / software engineering::UMZ Software Engineering
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues::TBD Technical design
thema EDItEUR::P Mathematics and Science::PH Physics::PHD Classical mechanics::PHDY Energy
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
topic_facet AI
Cybersecurity
Deep Learning
Edge Computing
Neural Networks
Processing Element
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TJ Electronics and communications engineering::TJF Electronics engineering::TJFM Automatic control engineering::TJFM1 Robotics
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQN Neural networks and fuzzy systems
thema EDItEUR::U Computing and Information Technology::UB Information technology: general topics
thema EDItEUR::U Computing and Information Technology::UM Computer programming / software engineering::UMZ Software Engineering
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues::TBD Technical design
thema EDItEUR::P Mathematics and Science::PH Physics::PHD Classical mechanics::PHDY Energy
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
url ONIX_20250310_9781040165034_9
work_keys_str_mv AT marchisioalberto energyefficiencyandrobustnessofadvancedmachinelearningarchitectures
AT shafiquemuhammad energyefficiencyandrobustnessofadvancedmachinelearningarchitectures