Cantitate/Preț
Produs
Total produse
Vezi coșul
Low-Computer Vision: Improve the Efficiency of Artificial Intelligence de George K. Thiruvathukal

Low-Computer Vision: Improve the Efficiency of Artificial Intelligence: Chapman & Hall/CRC Computer Vision

Editat de George K. Thiruvathukal, Yung-Hsiang Lu, Jaeyoun Kim, Yiran Chen, Bo Chen
en Limba Engleză Hardback – 23 feb 2022

Resursele care însoțesc volumul Low-Computer Vision reprezintă o arhivă tehnică prețioasă, fiind fundamentate pe soluțiile premiate în cadrul competiției anuale IEEE Low-Power Computer Vision Challenge. Ne-a atras atenția modul în care editorii, coordonați de George K. Thiruvathukal, reușesc să transforme competiția academică într-un manual riguros de inginerie aplicată, axat pe eficiența energetică pentru sisteme alimentate de baterii, precum dronele (UAV) sau dispozitivele mobile.

Considerăm că forța acestui volum rezidă în abordarea sa stratificată. Structura este una progresivă: prima secțiune stabilește contextul teoretic printr-un studiu amplu asupra rețelelor neurale profunde eficiente, în timp ce a doua secțiune disecă implementările concrete ale câștigătorilor. Sunt explorate teme critice precum cuantizarea uniformă pentru inferență rapidă și programarea rețelelor pe sisteme eterogene de tip SoC (System on Chip). Ca și Vivienne Sze în Efficient Processing of Deep Neural Networks, editorii de față distilează experiența reală în principii acționabile, însă cu un accent mult mai pronunțat pe rezultatele validate în competiții de profil.

În contextul operei sale, George K. Thiruvathukal continuă direcția începută în Low-Power Computer Vision, rafinând metodologiile de optimizare. Dacă în Intermediate C Programming autorul se concentra pe calitatea codului la nivel de bază, aici miza este mutată pe intersecția complexă dintre algoritmi și limitările fizice ale hardware-ului. Volumul nu se limitează la teorie, ci oferă date concrete prin cele 58 de tabele și peste 160 de ilustrații, documentând modul în care designul hardware și strategiile software pot reduce drastic consumul de energie fără a sacrifica precizia detectării vizuale.

Citește tot Restrânge

Din seria Chapman & Hall/CRC Computer Vision

Preț: 59237 lei

Preț vechi: 74047 lei
-20%

Puncte Express: 889

Carte indisponibilă temporar

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă

Specificații

ISBN-13: 9780367744700
ISBN-10: 0367744708
Pagini: 436
Ilustrații: 58 Tables, black and white; 61 Line drawings, color; 39 Line drawings, black and white; 1 Halftones, color; 62 Illustrations, color; 39 Illustrations, black and white
Dimensiuni: 156 x 234 x 28 mm
Greutate: 0.79 kg
Ediția:1
Editura: CRC Press
Colecția Chapman and Hall/CRC
Seria Chapman & Hall/CRC Computer Vision

Public țintă

Academic, Postgraduate, and Professional

De ce să citești această carte

Recomandăm această lucrare profesioniștilor și cercetătorilor care dezvoltă soluții de inteligență artificială pentru dispozitive edge. Cititorul câștigă acces direct la metodologiile premiate IEEE, învățând cum să optimizeze rețelele neurale pentru latență scăzută și consum minim. Este un ghid esențial pentru oricine dorește să implementeze computer vision pe hardware limitat, unde fiecare miliwatt contează.

Despre autor

George K. Thiruvathukal este o figură centrală în cercetarea sistemelor de calcul, ocupând poziții academice la Loyola University și Northwestern University (departamentul ECE). Expertiza sa acoperă ingineria software și sistemele distribuite, fiind totodată implicat în mediul antreprenorial prin Zirve! Technologies LLC. Prin activitatea sa de editor pentru seria Chapman & Hall/CRC Computer Vision, acesta a devenit un promotor al eficienței în AI, conectând rigorea academică de aplicațiile industriale practice prin documentarea competițiilor internaționale de profil.

Notă biografică

George K. Thiruvathukal is a professor of Computer Science at Loyola University Chicago, Illinois, USA. He is also a visiting faculty at Argonne National Laboratory. His research areas include high performance and distributed computing, software
engineering, and programming languages.
Yung-Hsiang Lu is a professor of Electrical and Computer Engineering at Purdue University, Indiana, USA. He is the first director of Purdue’s John Martinson Engineering Entrepreneurial Center. He is a fellow of the IEEE and distinguished scientist of the ACM. His research interests include computer vision, mobile systems, and cloud computing.
Jaeyoun Kim is a technical program manager at Google, California, USA. He leads AI research projects, including MobileNets and TensorFlow Model Garden, to build state-of-the-art machine learning models and modeling libraries for computer vision and natural language processing.
Yiran Chen is a professor of Electrical and Computer Engineering at Duke University, North Carolina, USA. He is a fellow of the ACM and the IEEE. His research areas include new memory and storage systems, machine learning and neuromorphic
computing, and mobile computing systems.
Bo Chen is the Director of AutoML at DJI, Guangdong, China. Before joining DJI, he was a researcher at Google, California, USA. His research interests are the optimization of neural network software and hardware as well as landing AI technology in products with stringent resource constraints.

Cuprins

Section I Introduction
Book Introduction 
Yung-Hsiang Lu, George K. Thiruvathukal, Jaeyoun Kim, Yiran Chen, and Bo Chen
History of Low-Power Computer Vision Challenge 
Yung-Hsiang Lu and Xiao Hu, Yiran Chen, Joe Spisak, Gaurav Aggarwal, Mike Zheng Shou, and George K. Thiruvathukal
Survey on Energy-Efficient Deep Neural Networks for Computer Vision 
Abhinav Goel, Caleb Tung, Xiao Hu, Haobo Wang, and Yung-Hsiang Lu and George K. Thiruvathukal
Section II Competition Winners

Hardware design and software practices for efficient neural network inference 
Yu Wang, Xuefei Ning, Shulin Zeng, Yi Kai, Kaiyuan Guo, and Hanbo Sun, Changcheng Tang, Tianyi Lu, Shuang Liang, and Tianchen Zhao
Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search
Xin Xia, Xuefeng Xiao, and Xing Wang
Fast Adjustable Threshold For Uniform Neural Network Quantization
Alexander Goncharenko, Andrey Denisov, and Sergey Alyamkin
Power-efficient Neural Network Scheduling on Heterogeneous SoCs
Ying Wang, Xuyi Cai, and Xiandong Zhao
Efficient Neural Network Architectures
Han Cai and Song Han
Design Methodology for Low Power Image Recognition Systems
Soonhoi Ha, EunJin Jeong, Duseok Kang, Jangryul Kim, and Donghyun Kang
Guided Design for Efficient On-device Object Detection Model
Tao Sheng and Yang Liu
Section III Invited Articles

Quantizing Neural Networks 
Marios Fournarakis, Markus Nagel, Rana Ali Amjad, Yelysei Bondarenko, Mart van Baalen, and Tijmen Blankevoort
A practical guide to designing efficient mobile architectures
Mark Sandler and Andrew Howard
A Survey of Quantization Methods for Efficient Neural Network Inference
Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael Mahoney, and Kurt Keutzer
Bibliography
Index

Recenzii

On device AI has become increasingly important for reasons of latency, privacy and overall autonomy as computing becomes more and more ambient. Moreover, making AI, in particular computer vision, efficient and run well in low resource computing environments using frameworks like PyTorch is a priority of the industry to enable this. The IEEE Low-Power Computer Vision Challenge is one such effort that has and continues to push the field forward allowing us to make progress in this area. Facebook has been a proud sponsor and supporter of this challenge since 2018 and this book presents the winners’ solutions from previous challenges and can guide researchers, engineers, and students to design efficient on device AI.
-- Joe Spisak, Product Lead at Facebook Artificial Intelligence
Computer vision is at the center of recent breakthroughs in artificial intelligence. Being able to process visual data in low-power computing environments will enable great advances in the field in areas such as edge computing and Internet of Things. This book presents work by experts in the field and their winning solutions. It is an indispensable resource for anyone interested creating AI technologies in resource constrained computing environments
-- Mark Liao, Director, Institute of Information Science, Academia Sinica
From mobile phones to wearable health monitors, improved energy efficiency is the enabling technology of everything we take for granted today. Computer vision is at the center of artificial intelligence and machine learning. Today, artificial intelligence and low power are often at different ends of the spectrum. Low-power computer vision will enable greater adoption of the technologies in battery-powered IoT (Internet of Things) systems. This book collects the winners’ solutions of the Low-Power Computer Vision Challenge and provides insight on how to improve efficiency of artificial intelligence.
-- Edwin Park, Principal Engineer at Qualcomm

Descriere

Energy efficiency is critical for running computer vision on battery-powered systems, such as mobile phones or UAVs (unmanned aerial vehicles, or drones). This book collects the methods that have won the annual IEEE Low-Power Computer Vision Challenges since 2015. The winners share their solutions and provide insight on how to improve the efficiency of machine learning systems.