東華大學圖書館 |

Artificial intelligence for edge computing

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Artificial intelligence for edge computing/ edited by Mudhakar Srivatsa, Tarek Abdelzaher, Ting He.
其他作者:	Srivatsa, Mudhakar.
出版者:	Cham :Springer International Publishing : : 2023.,
面頁冊數:	xiv, 365 p. :ill., digital ;24 cm.
內容註:	Part I: Core Problems -- Chapter 1: Neural Network Models for Time Series Data -- Chapter 2: Self-Supervised Learning from Unlabeled IoT Data -- Chapter 3: On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models -- Chapter 4: Out of Distribution Detection -- Chapter 5: Model Compression for Edge Computing -- Part II: Distributed Problems -- Chapter 6: Communication Efficient Distributed Learning -- Chapter 7: Coreset-based Data Reduction for Machine Learning at the Edge -- Chapter 8: Lightweight Collaborative Perception at the Edge -- Chapter 9: Dynamic Placement of Services at the Edge -- Chapter 10: Joint Service Placement and Request Scheduling at the Edge -- Part III: Cross-cutting Thoughts -- Chapter 11: Criticality-based Data Segmentation and Resource Allocation in Machine Inference Pipelines -- Chapter 12: Model Operationalization at Edge Devices.
Contained By:	Springer Nature eBook
標題:	Edge computing. -
電子資源:	https://doi.org/10.1007/978-3-031-40787-1
ISBN:	9783031407871

Artificial intelligence for edge computing
Artificial intelligence for edge computing[electronic resource] /edited by Mudhakar Srivatsa, Tarek Abdelzaher, Ting He. - Cham :Springer International Publishing :2023. - xiv, 365 p. :ill., digital ;24 cm.

Part I: Core Problems -- Chapter 1: Neural Network Models for Time Series Data -- Chapter 2: Self-Supervised Learning from Unlabeled IoT Data -- Chapter 3: On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models -- Chapter 4: Out of Distribution Detection -- Chapter 5: Model Compression for Edge Computing -- Part II: Distributed Problems -- Chapter 6: Communication Efficient Distributed Learning -- Chapter 7: Coreset-based Data Reduction for Machine Learning at the Edge -- Chapter 8: Lightweight Collaborative Perception at the Edge -- Chapter 9: Dynamic Placement of Services at the Edge -- Chapter 10: Joint Service Placement and Request Scheduling at the Edge -- Part III: Cross-cutting Thoughts -- Chapter 11: Criticality-based Data Segmentation and Resource Allocation in Machine Inference Pipelines -- Chapter 12: Model Operationalization at Edge Devices.

It is undeniable that the recent revival of artificial intelligence (AI) has significantly changed the landscape of science in many application domains, ranging from health to defense and from conversational interfaces to autonomous cars. With terms such as "Google Home", "Alexa", and "ChatGPT" becoming household names, the pervasive societal impact of AI is clear. Advances in AI promise a revolution in our interaction with the physical world, a domain where computational intelligence has always been envisioned as a transformative force toward a better tomorrow. Depending on the application family, this domain is often referred to as Ubiquitous Computing, Cyber-Physical Computing, or the Internet of Things. The underlying vision is driven by the proliferation of cheap embedded computing hardware that can be integrated easily into myriads of everyday devices from consumer electronics, such as personal wearables and smart household appliances, to city infrastructure and industrial process control systems. One common trait across these applications is that the data that the application operates on come directly (typically via sensors) from the physical world. Thus, from the perspective of communication network infrastructure, the data originate at the network edge. From a performance standpoint, there is an argument to be made that such data should be processed at the point of collection. Hence, a need arises for Edge AI -- a genre of AI where the inference, and sometimes even the training, are performed at the point of need, meaning at the edge where the data originate. The book is broken down into three parts: core problems, distributed problems, and other cross-cutting issues. It explores the challenges arising in Edge AI contexts. Some of these challenges (such as neural network model reduction to fit resource-constrained hardware) are unique to the edge environment. They need a novel category of solutions that do not parallel more typical concerns in mainstream AI. Others are adaptations of mainstream AI challenges to the edge space. An example is overcoming the cost of data labeling. The labeling problem is pervasive, but its solution in the IoT application context is different from other contexts. This book is not a survey of the state of the art. With thousands of publications appearing in AI every year, such a survey is doomed to be incomplete on arrival. It is also not a comprehensive coverage of all the problems in the space of Edge AI. Different applications pose different challenges, and a more comprehensive coverage should be more application specific. Instead, this book covers some of the more endemic challenges across the range of IoT/CPS applications. To offer coverage in some depth, we opt to cover mainly one or a few representative solutions for each of these endemic challenges in sufficient detail, rather that broadly touching on all relevant prior work. The underlying philosophy is one of illustrating by example. The solutions are curated to offer insight into a way of thinking that characterizes Edge AI research and distinguishes its solutions from their more mainstream counterparts.

ISBN: 9783031407871

Standard No.: 10.1007/978-3-031-40787-1doiSubjects--Topical Terms:

3489844
Edge computing.

LC Class. No.: QA76.583

Dewey Class. No.: 006.3

Artificial intelligence for edge computing
LDR:05059nmm a2200325 a 4500 001 2390042
003 DE-He213
005 20231221130615.0
006 m d
007 cr nn 008maaau
008 250916s2023 sz s 0 eng d
020 $a 9783031407871 $q (electronic bk.)
020 $a 9783031407864 $q (paper)
024 7 $a 10.1007/978-3-031-40787-1 $2 doi
035 $a 978-3-031-40787-1
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.583
072 7 $a UYQ $2 bicssc
072 7 $a TEC009000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.3 $2 23
090 $a QA76.583 $b .A791 2023
245 0 0 $a Artificial intelligence for edge computing $h [electronic resource] / $c edited by Mudhakar Srivatsa, Tarek Abdelzaher, Ting He.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2023.
300 $a xiv, 365 p. : $b ill., digital ; $c 24 cm.
505 0 $a Part I: Core Problems -- Chapter 1: Neural Network Models for Time Series Data -- Chapter 2: Self-Supervised Learning from Unlabeled IoT Data -- Chapter 3: On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models -- Chapter 4: Out of Distribution Detection -- Chapter 5: Model Compression for Edge Computing -- Part II: Distributed Problems -- Chapter 6: Communication Efficient Distributed Learning -- Chapter 7: Coreset-based Data Reduction for Machine Learning at the Edge -- Chapter 8: Lightweight Collaborative Perception at the Edge -- Chapter 9: Dynamic Placement of Services at the Edge -- Chapter 10: Joint Service Placement and Request Scheduling at the Edge -- Part III: Cross-cutting Thoughts -- Chapter 11: Criticality-based Data Segmentation and Resource Allocation in Machine Inference Pipelines -- Chapter 12: Model Operationalization at Edge Devices.
520 $a It is undeniable that the recent revival of artificial intelligence (AI) has significantly changed the landscape of science in many application domains, ranging from health to defense and from conversational interfaces to autonomous cars. With terms such as "Google Home", "Alexa", and "ChatGPT" becoming household names, the pervasive societal impact of AI is clear. Advances in AI promise a revolution in our interaction with the physical world, a domain where computational intelligence has always been envisioned as a transformative force toward a better tomorrow. Depending on the application family, this domain is often referred to as Ubiquitous Computing, Cyber-Physical Computing, or the Internet of Things. The underlying vision is driven by the proliferation of cheap embedded computing hardware that can be integrated easily into myriads of everyday devices from consumer electronics, such as personal wearables and smart household appliances, to city infrastructure and industrial process control systems. One common trait across these applications is that the data that the application operates on come directly (typically via sensors) from the physical world. Thus, from the perspective of communication network infrastructure, the data originate at the network edge. From a performance standpoint, there is an argument to be made that such data should be processed at the point of collection. Hence, a need arises for Edge AI -- a genre of AI where the inference, and sometimes even the training, are performed at the point of need, meaning at the edge where the data originate. The book is broken down into three parts: core problems, distributed problems, and other cross-cutting issues. It explores the challenges arising in Edge AI contexts. Some of these challenges (such as neural network model reduction to fit resource-constrained hardware) are unique to the edge environment. They need a novel category of solutions that do not parallel more typical concerns in mainstream AI. Others are adaptations of mainstream AI challenges to the edge space. An example is overcoming the cost of data labeling. The labeling problem is pervasive, but its solution in the IoT application context is different from other contexts. This book is not a survey of the state of the art. With thousands of publications appearing in AI every year, such a survey is doomed to be incomplete on arrival. It is also not a comprehensive coverage of all the problems in the space of Edge AI. Different applications pose different challenges, and a more comprehensive coverage should be more application specific. Instead, this book covers some of the more endemic challenges across the range of IoT/CPS applications. To offer coverage in some depth, we opt to cover mainly one or a few representative solutions for each of these endemic challenges in sufficient detail, rather that broadly touching on all relevant prior work. The underlying philosophy is one of illustrating by example. The solutions are curated to offer insight into a way of thinking that characterizes Edge AI research and distinguishes its solutions from their more mainstream counterparts.
650 0 $a Edge computing. $3 3489844
650 0 $a Artificial intelligence. $3 516317
650 1 4 $a Computational Intelligence. $3 1001631
650 2 4 $a Robotics. $3 519753
650 2 4 $a Machine Learning. $3 3382522
650 2 4 $a Computer and Information Systems Applications. $3 3538505
650 2 4 $a Computer Communication Networks. $3 775497
700 1 $a Srivatsa, Mudhakar. $3 1265173
700 1 $a Abdelzaher, Tarek. $3 2133951
700 1 $a He, Ting. $3 3756136
710 2 $a SpringerLink (Online service) $3 836513
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-3-031-40787-1
950 $a Intelligent Technologies and Robotics (SpringerNature-42732)