Edge Intelligence: Challenges and Opportunities of Near-Sensor Machine Learning Applications

The number of connected IoT devices is expected to reach over 20 billion by 2020. These range from basic sensor nodes that log and report the data for cloud processing, to the ones on the edge, that are capable of processing and analyzing the incoming information and taking an action accordingly. Machine learning, and in particular deep learning, is the defacto processing paradigm for intelligently processing these immense volumes of data. However, the resource inhibited environment of edge devices, owing to their limited energy budget, and low compute capabilities, render them a challenging platform for deployment of desired data analytics, particularly in realtime applications. In this paper therefore, we argue that for a wide range of emerging applications edge intelligence is a necessary evolutionary need, and thus we provide a summary of the challenges and opportunities that arise from this need. We showcase through a case study regarding computer vision for commercial drones, how these opportunities can be taken advantage, and how some of the challenges can be potentially addressed.

[1]  Luca Benini,et al.  CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data , 2017, ICDSC.

[2]  Xin Yao,et al.  The Future of Camera Networks: Staying Smart in a Chaotic World , 2017, ICDSC.

[3]  Muhammad Shafique,et al.  An overview of next-generation architectures for machine learning: Roadmap, opportunities and challenges in the IoT era , 2018, 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[4]  Weisong Shi,et al.  Edge Computing: Vision and Challenges , 2016, IEEE Internet of Things Journal.

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[8]  Martin Margala,et al.  Highly efficient digital CMOS accelerator for image and graphics processing , 2002, 15th Annual IEEE International ASIC/SOC Conference.

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

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

[11]  Tao Zhang,et al.  Fog and IoT: An Overview of Research Opportunities , 2016, IEEE Internet of Things Journal.

[12]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.

[13]  Michael J. Behe,et al.  The edge of intelligence , 2009 .

[14]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Christos-Savvas Bouganis,et al.  DroNet: Efficient convolutional neural network detector for real-time UAV applications , 2018, 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[16]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Eunhyeok Park,et al.  Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications , 2015, ICLR.

[18]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[19]  David A. Ferrucci.  IBM's Watson/DeepQA , 2011, SIGARCH Comput. Archit. News.

[20]  David A. Patterson,et al.  In-datacenter performance analysis of a tensor processing unit , 2017, 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA).

[21]  Thomas B. Preußer,et al.  Inference of quantized neural networks on heterogeneous all-programmable devices , 2018, 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[22]  Sergio Guadarrama,et al.  Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[24]  Kevin Curran,et al.  Cloud Computing Security , 2011, Int. J. Ambient Comput. Intell..