Edge Intelligence: The Convergence of Humans, Things, and AI

Edge AI and Human Augmentation are two major technology trends, driven by recent advancements in edge computing, IoT, and AI accelerators. As humans, things, and AI continue to grow closer together, systems engineers and researchers are faced with new and unique challenges. In this paper, we analyze the role of edge computing and AI in the cyber-human evolution, and identify challenges that edge computing systems will consequently be faced with. We take a closer look at how a cyber-physical fabric will be complemented by AI operationalization to enable seamless end-to-end edge intelligence systems.

[1]  Blaise Agüera y Arcas,et al.  Federated Learning of Deep Networks using Model Averaging , 2016, ArXiv.

[2]  Schahram Dustdar,et al.  LEONORE -- Large-Scale Provisioning of Resource-Constrained IoT Deployments , 2015, 2015 IEEE Symposium on Service-Oriented System Engineering.

[3]  Parijat Dube,et al.  ModelOps: Cloud-Based Lifecycle Management for Reliable and Trusted AI , 2019, 2019 IEEE International Conference on Cloud Engineering (IC2E).

[4]  Schahram Dustdar,et al.  A Serverless Real-Time Data Analytics Platform for Edge Computing , 2017, IEEE Internet Computing.

[5]  Laurence T. Yang,et al.  Mobility in Publish/Subscribe Systems , 2010 .

[6]  Aaron Klein,et al.  Efficient and Robust Automated Machine Learning , 2015, NIPS.

[7]  Albert Bifet,et al.  Efficient Online Evaluation of Big Data Stream Classifiers , 2015, KDD.

[8]  Ben Goertzel,et al.  Distributed, decentralized, and democratized artificial intelligence , 2019, Technological Forecasting and Social Change.

[9]  Teruo Higashino,et al.  Edge-centric Computing: Vision and Challenges , 2015, CCRV.

[10]  Schahram Dustdar,et al.  A Middleware Infrastructure for Utility-Based Provisioning of IoT Cloud Systems , 2016, 2016 IEEE/ACM Symposium on Edge Computing (SEC).

[11]  Roberto Morabito,et al.  Virtualization on Internet of Things Edge Devices With Container Technologies: A Performance Evaluation , 2017, IEEE Access.

[12]  Jinfeng Yi,et al.  Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach , 2018, ICLR.

[13]  Schahram Dustdar,et al.  Portable Energy-Aware Cluster-Based Edge Computers , 2018, 2018 IEEE/ACM Symposium on Edge Computing (SEC).

[14]  Weisong Shi,et al.  The Promise of Edge Computing , 2016, Computer.

[15]  Jennifer Chu-Carroll,et al.  Building Watson: An Overview of the DeepQA Project , 2010, AI Mag..

[16]  David Gunning,et al.  DARPA's explainable artificial intelligence (XAI) program , 2019, IUI.

[17]  Zhuo Chen,et al.  Edge Analytics in the Internet of Things , 2015, IEEE Pervasive Computing.

[18]  Laurence T. Yang,et al.  Recent Advances in Mobile Agent‐Oriented Applications , 2010 .

[19]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[20]  João Gama,et al.  A survey on concept drift adaptation , 2014, ACM Comput. Surv..

[21]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[22]  Paramvir Bahl,et al.  The Case for VM-Based Cloudlets in Mobile Computing , 2009, IEEE Pervasive Computing.

[23]  Rajiv Ranjan,et al.  Osmotic Message-Oriented Middleware for the Internet of Things , 2018, IEEE Cloud Computing.

[24]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[25]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[26]  Tian Li,et al.  Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads , 2017, Proc. VLDB Endow..

[27]  Mahadev Satyanarayanan,et al.  Towards wearable cognitive assistance , 2014, MobiSys.

[28]  Klaus-Robert Müller,et al.  Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models , 2017, ArXiv.

[29]  Larry S. Davis,et al.  ModelHub: Deep Learning Lifecycle Management , 2017, 2017 IEEE 33rd International Conference on Data Engineering (ICDE).

[30]  Xiaogang Wang,et al.  Understanding collective crowd behaviors: Learning a Mixture model of Dynamic pedestrian-Agents , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Seetharami R. Seelam,et al.  IBM Deep Learning Service , 2017, IBM J. Res. Dev..

[32]  Xin Zhang,et al.  TFX: A TensorFlow-Based Production-Scale Machine Learning Platform , 2017, KDD.

[33]  Schahram Dustdar,et al.  EMMA: Distributed QoS-Aware MQTT Middleware for Edge Computing Applications , 2018, 2018 IEEE International Conference on Cloud Engineering (IC2E).

[34]  Anthony Rowe,et al.  Sensor Data as a Service -- A Federated Platform for Mobile Data-centric Service Development and Sharing , 2013, 2013 IEEE International Conference on Services Computing.

[35]  Chen Yu,et al.  Multi-device, Multi-tenant Model Selection with GP-EI , 2018, AISTATS.

[36]  Schahram Dustdar,et al.  Enabling a Smart City Application Ecosystem , 2016 .

[37]  Mahadev Satyanarayanan,et al.  From the Editor in Chief: Augmenting Cognition , 2004, IEEE Pervasive Comput..

[38]  Mahadev Satyanarayanan,et al.  The Emergence of Edge Computing , 2017, Computer.

[39]  Marc'Aurelio Ranzato,et al.  Large Scale Distributed Deep Networks , 2012, NIPS.

[40]  Peng Liu,et al.  ParaDrop: Enabling Lightweight Multi-tenancy at the Network’s Extreme Edge , 2016, 2016 IEEE/ACM Symposium on Edge Computing (SEC).

[41]  Jon Crowcroft,et al.  Unikernels: library operating systems for the cloud , 2013, ASPLOS '13.

[42]  Ben Goertzel,et al.  Contemporary Approaches to Artificial General Intelligence , 2007, Artificial General Intelligence.