Abstract
AI is a broad field of research that includes many methods of research value. However, due to the characteristics of edge computing in its operating structure and computing resources, deep learning has become the most closely related and representative method in AI for edge computing. In addition, due to the limitations of resources in edge computing, there is a lack of targeted solutions for resource-intensive deep learning. Therefore, in this book we focus on deep learning that require high computing resources. With respect to CV, NLP, and AI, DL is adopted in a myriad of applications and corroborates its superior performance by LeCun et al. (Nature 521(7553):436–444, 2015). Currently, a large number of GPUs, TPUs, or FPGAs are required to be deployed in the cloud to process DL service requests.Through the introduction of the previous two chapters, this book has made an in-depth analysis of the development bottlenecks of the current cloud computing model. The reader can understand that the current response time requirements of some deep learning applications are extremely demanding, and cloud computing can no longer meet the needs. Therefore, it is necessary to consider transferring the task of deep learning to the edge computing framework. Nonetheless, the edge computing architecture, on account of it covers a large number of distributed edge devices, can be utilized to better serve DL. Certainly, edge devices typically have limited computing power or power consumption compared to the cloud. Therefore, the combination of DL and edge computing is not straightforward and requires a comprehensive understanding of DL models and edge computing features for design and deployment. In this section, we compendiously introduce DL and related technical terms, paving the way for discussing the integration of DL and edge computing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
H. Li, K. Ota, M. Dong, Learning IoT in edge: deep learning for the Internet of Things with edge computing. IEEE Netw. 32(1), 96–101 (2018)
S.S. Haykin, K. Elektroingenieur, Neural Networks and Learning Machines (Pearson Prentice Hall, Englewood Cliffs, 2009)
R. Collobert, S. Bengio, Links between perceptrons, MLPs and SVMs, in Proceeding of the Twenty-first International Conference on Machine Learning (ICML 2004) (2004), p. 23
C.D. Manning, C.D. Manning, H. Schütze, Foundations of Statistical Natural Language Processing (MIT Press, New York, 1999)
M.D. Zeiler, R. Fergus, Visualizing and understanding convolutional networks, in 2014 European Conference on Computer Vision (ECCV 2014) (2014), pp. 818–833
I. Goodfellow, J. Pouget-Abadie, M. Mirza, et al., Generative adversarial nets, in Advances in Neural Information Processing Systems 27 (NeurIPS 2014) (2014), pp. 2672–2680
J. Schmidhuber, Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
S.J. Pan, Q. Yang, A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
G. Hinton, O. Vinyals, J. Dean, Distilling the knowledge in a neural network (2015). ar**v preprint:1503.02531
S.S. Mousavi, M. Schukat, E. Howley, Deep reinforcement learning: an overview, in Proceeding of the 2016 SAI Intelligent Systems Conference (IntelliSys 2016) (2016), pp. 426–440
V. Mnih, K. Kavukcuoglu, D. Silver, et al., Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
H. Van Hasselt, A. Guez, D. Silver, Deep reinforcement learning with double Q-learning, in Proceeding of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI 2016) (2016), pp. 2094–2100
Z. Wang, T. Schaul, M. Hessel, et al., Dueling network architectures for deep reinforcement learning, in Proceeding of the 33rd International Conference on Machine Learning (ICML 2016) (2016), pp. 1995–2003
T.P. Lillicrap, J.J. Hunt, A. Pritzel, et al., Continuous control with deep reinforcement learning, in Proceeding of the 6th International Conference on Learning Representations (ICLR 2016) (2016)
V. Mnih, A.P. Badia, M. Mirza, et al., Asynchronous methods for deep reinforcement learning, in Proceeding of the 33rd International Conference on Machine Learning (ICML 2016) (2016), pp. 1928–1937
J. Schulman, F. Wolski, P. Dhariwal, et al., Proximal policy optimization algorithms (2017). ar**v preprint:1707.06347
R.S. Sutton, D. McAllester, S. Singh, Y. Mansour, Policy gradient methods for reinforcement learning with function approximation, in Proceeding of the 12th International Conference on Neural Information Processing Systems (NeurIPS 1999) (1999), pp. 1057–1063
A.S. Monin, A.M. Yaglom, Large scale distributed deep networks, in Proceeding of Advances in Neural Information Processing Systems 25 (NeurIPS 2012) (2012), pp. 1223–1231
Y. Zou, X. **, Y. Li, et al., Mariana: Tencent deep learning platform and its applications. Proc. VLDB Endow.7(13), 1772–1777 (2014)
X. Chen, A. Eversole, G. Li, et al., Pipelined back-propagation for context-dependent deep neural networks, in Proceeding of 13th Annual Conference of the International Speech Communication Association (INTERSPEECH 2012) (2012), pp. 26–29
M. Stevenson, R. Winter, et al., 1-Bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs, in 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014) (2014), pp. 1058–1062
A. Coates, B. Huval, T. Wang, et al., Deep learning with cots HPC systems, in Proceeding of the 30th International Conference on Machine Learning (PMLR 2013) (2013), pp. 1337–1345
P. Moritz, R. Nishihara, I. Stoica, and M. I. Jordan, SparkNet: Training Deep Networks in Spark. ar**v preprint:1511.06051, 2015.
Theano is a Python Library that Allows you to Define, Optimize, and Evaluate Mathematical Expressions Involving Multi-Dimensional Arrays Efficiently. https://github.com/Theano/Theano
M. Abadi, P. Barham, et al., TensorFlow: a system for large-scale machine learning, in Proceeding of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI 2016) (2016), pp. 265–283
Y. Jia, E. Shelhamer, et al., Caffe: convolutional architecture for fast feature embedding, in Proceedings of the 22nd ACM international conference on Multimedia (2014), pp. 675–678
Géron, Aurélien, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (O’Reilly Media, Sebastopol, 2019)
A. Paszke, S. Gross, et al., PyTorch: an imperative style, high-performance deep learning library, in Advances in Neural Information Processing Systems (2019), pp. 8024–8035
Y. LeCun, Y. Bengio, G. Hinton, Deep learning. Nature 521(7553), 436–444 (2015)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2020 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Wang, X., Han, Y., Leung, V.C.M., Niyato, D., Yan, X., Chen, X. (2020). Fundamentals of Artificial Intelligence. In: Edge AI. Springer, Singapore. https://doi.org/10.1007/978-981-15-6186-3_3
Download citation
DOI: https://doi.org/10.1007/978-981-15-6186-3_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-6185-6
Online ISBN: 978-981-15-6186-3
eBook Packages: Computer ScienceComputer Science (R0)