Artificial Intelligence for Edge Computing

Mudhakar Srivatsa received the Ph.D. degree in Computer Science from Georgia Tech. He is a distinguished engineer at the Automation and AI research department in IBM T. J. Watson Research Center. His work is focussed on cloud-native data and AI architectures for spatial and time series data. He is an IBM master inventor with over 100 granted US patents, over 100 refereed publications, a recipient of IBM corporate award, IBM Recognition Experience Honoree, outstanding technical achievement awards and research division awards. His co-led a global collaboration across research, product development and consulting organizations to develop Watson Core Spatial and Time series library has been adopted in multiple product offerings. Tarek Abdelzaher received his Ph.D. degree in Computer Science and Engineering from the University of Michigan in 1999. He is presently a Sohaib and Sara Abbasi Professor of Computer Science and a Willett Faculty Scholarat the University of Illinois. Abdelzaher has over 300 refereed publications in Real-time Computing, Distributed Systems, Sensor Networks, and IoT, with more than 41,000 citations according to Google Scholar, and an H-index of 96. He served as Editor-in-Chief of the Journal of Real-Time Systems for many years, and as an Associate Editor of multiple journals including IEEE TMC, IEEE TPDS, ACM ToSN, ACM TIoT, and ACM ToIT. He also chaired several top conferences in his field, including RTSS, Sensys, Infocom, ICDCS, IPSN, RTAS, DCoSS, EWSN, IWQoS, and ICAC. Abdelzaher received the IEEE Outstanding Technical Achievement and Leadership Award in Real-time Systems (2012), a Xerox Research Award (2011), and over a dozen best paper awards. He is a fellow of IEEE and ACM.Ting He received the Ph.D. degree in Electrical and Computer Engineering from Cornell University. Dr. He is an Associate Professor in the School of Electrical Engineering and Computer Science at the Pennsylvania State University, University Park, PA. Her interests reside at the intersection of computer networking, distributed computing, and machine learning. Dr. He is a Senior Member of IEEE. She has served as Associate Editor for IEEE Transactions on Communications and IEEE/ACM Transactions on Networking, General Co-Chair of IEEE RTCSA, TPC Co-Chair of IEEE ICCCN, Area TPC Chair of IEEE INFOCOM, and TPC member of many international conferences on networking and distributed computing. She received multiple awards from IBM and International Technology Alliance (ITA) for technical contributions, and multiple best paper awards from IEEE Communications Society, IEEE ICDCS, ACM SIGMETRICS, and IEEE ICASSP.

• 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.