Abstract
Deep Learning (DL) has become a crucial technology for multimedia computing. It offers a powerful instrument to automatically produce high-level abstractions of complex multimedia data, which can be exploited in a number of applications, including object detection and recognition, speech-to- text, media retrieval, multimodal data analysis, and so on. The availability of affordable large-scale parallel processing architectures, and the sharing of effective open-source codes implementing the basic learning algorithms, caused a rapid diffusion of DL methodologies, bringing a number of new technologies and applications that outperform, in most cases, traditional machine learning technologies. In recent years, the possibility of implementing DL technologies on mobile devices has attracted significant attention. Thanks to this technology, portable devices may become smart objects capable of learning and acting. The path toward these exciting future scenarios, however, entangles a number of important research challenges. DL architectures and algorithms are hardly adapted to the storage and computation resources of a mobile device. Therefore, there is a need for new generations of mobile processors and chipsets, small footprint learning and inference algorithms, new models of collaborative and distributed processing, and a number of other fundamental building blocks. This survey reports the state of the art in this exciting research area, looking back to the evolution of neural networks, and arriving to the most recent results in terms of methodologies, technologies, and applications for mobile environments.
- Caffe for Android. Retrieved from https://github.com/sh1r0/caffe-android-lib. Accessed: 2017-02-20.Google Scholar
- CaffeOnSpark. Retrieved from https://github.com/yahoo/CaffeOnSpark. Accessed: 2017-02-20.Google Scholar
- Chainer. Retrieved from http://chainer.org. Accessed: 2017-02-20.Google Scholar
- Keras. Retrieved from https://keras.io/. Accessed: 2017-02-20.Google Scholar
- Lasagne. Retrieved from https://lasagne.readthedocs.io. Accessed: 2017-02-20.Google Scholar
- MXNet. Retrieved from http://mxnet.io/. Accessed: 2017-02-20.Google Scholar
- Neon. Retrieved from http://neon.nervanasys.com/index.html/index.html. Accessed: 2017-02-20.Google Scholar
- PyTorch. Retrieved from http://pytorch.org/. Accessed: 2017-02-20.Google Scholar
- TensorFlowOnSpark. Retrieved from https://github.com/yahoo/TensorFlowOnSpark. Accessed: 2017-02-20.Google Scholar
- Torch. Retrieved from http://torch.ch/. Accessed: 2017-02-20.Google Scholar
- Torch for Android. Retrieved from https://github.com/soumith/torch-android. Accessed: 2017-02-20.Google Scholar
- Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, et al. 2016. TensorFlow: Large-scale machine learning on heterogeneous distributed systems. CoRR abs/1603.04467 (2016). Retrieved from http://arxiv.org/abs/1603.04467.Google Scholar
- Richard Adhikari. 2016. Google, Movidius to Bring Deep Learning to Mobile Devices. Retrieved from http://www.technewsworld.com/story/83052.html (Jan 2016).Google Scholar
- Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermüller, Dzmitry Bahdanau, Nicolas Ballas, et al. 2016. Theano: A python framework for fast computation of mathematical expressions. CoRR abs/1605.02688 (2016). Retrieved from http://arxiv.org/abs/1605.02688.Google Scholar
- Jose M. Alvarez and Lars Petersson. 2016. DecomposeMe: Simplifying ConvNets for end-to-end learning. CoRR abs/1606.05426 (2016). Retrieved from http://arxiv.org/abs/1606.05426.Google Scholar
- Torbjrn Morland Amund Tveit and Thomas Brox Rst. DeepLearningKit—An Open Source Deep Learning Framework for Apple’s iOS, OS X, and tvOS developed in Metal and Swift. Retrieved from https://arxiv.org/abs/1605.04614"⟩https://arxiv.org/abs/1605.04614. Accessed: 2017-02-20.Google Scholar
- Sajid Anwar, Kyuyeon Hwang, and Wonyong Sung. 2017. Structured pruning of deep convolutional neural networks. J. Emerg. Technol. Comput. Syst. 13, 3 (2017), 32:1--32:18. Google Scholar
Digital Library
- David Bacon, Rodric Rabbah, and Sunil Shukla. 2013. FPGA programming for the masses. Queue 11, 2, Article 40 (Feb. 2013), 13 pages. Google Scholar
Digital Library
- Dana H. Ballard. Modular learning in neural networks. In Proceedings of the 6th National Conference on Artificial Intelligence, K. Forbus and H. Shrobe (Eds.). Morgan Kaufmann, San Francisco, CA. 279--284. Google Scholar
Digital Library
- Yoshua Bengio, Pascal Lamblin, Dan Popovici, and Hugo Larochelle. 2007. Greedy layer-wise training of deep networks. In Advances in Neural Information Processing Systems 19, P. B. Schölkopf, J. C. Platt, and T. Hoffman (Eds.). MIT Press, 153--160. Google Scholar
Digital Library
- Y. Bengio, P. Simard, and P. Frasconi. 1994. Learning long-term dependencies with gradient descent is difficult. Trans. Neur. Netw. 5, 2 (1994), 157--166. Google Scholar
Digital Library
- B. Biggio, G. Fumera, and F. Roli. 2014. Security evaluation of pattern classifiers under attack. IEEE Trans. Knowl. Data Eng. 26(4) (2014), 984--996. Google Scholar
Digital Library
- G. Castellano, A. M. Fanelli, and M. Pelillo. 1997. An iterative pruning algorithm for feedforward neural networks. IEEE Trans. Neural Netw. 8, 3 (1997), 519--531. Google Scholar
Digital Library
- Kumar Chellapilla, Sidd Puri, and Patrice Simard. 2006. High performance convolutional neural networks for document processing. In Proceedings of the 10th International Workshop on Frontiers in Handwriting Recognition. Suvisoft.Google Scholar
- Tianshi Chen, Zidong Du, Ninghui Sun, Jia Wang, Chengyong Wu, Yunji Chen, and Olivier Temam. 2014. DianNao: A small-footprint high-throughput accelerator for ubiquitous machine-learning. In Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS’14). ACM, New York, 269--284. Google Scholar
Digital Library
- Wenlin Chen, James Wilson, Stephen Tyree, Kilian Q. Weinberger, and Yixin Chen. 2015. Compressing neural networks with the hashing trick. In Proceedings of the 32nd International Conference on Machine Learning (ICML’15). 2285--2294. Google Scholar
Digital Library
- Y. Chen, T. Luo, S. Liu, S. Zhang, L. He, J. Wang, L. Li, T. Chen, Z. Xu, N. Sun, and O. Temam. 2014. DaDianNao: A machine-learning supercomputer. In Proceedings of the 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture. 609--622. Google Scholar
Digital Library
- Y. H. Chen, T. Krishna, J. Emer, and V. Sze. 2016. 14.5 Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks. In Proceedings of the 2016 IEEE International Solid-State Circuits Conference (ISSCC’16). 262--263.Google Scholar
- Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. CUDNN: Efficient primitives for deep learning. arXiv:1410.0759 (2014).Google Scholar
- Trishul Chilimbi, Yutaka Suzue, Johnson Apacible, and Karthik Kalyanaraman. 2014. Project Adam: Building an efficient and scalable deep learning training system. In Proceedings of the 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI’14). USENIX Association, Broomfield, CO, 571--582. Google Scholar
Digital Library
- Wonje Choi, Karthi Duraisamy, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Radu Marculescu, and Diana Marculescu. 2016. Hybrid network-on-chip architectures for accelerating deep learning kernels on heterogeneous manycore platforms. In Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems (CASES’16). ACM, New York, Article 13, 10 pages. Google Scholar
Digital Library
- Dan C. Cireşan, Ueli Meier, Jonathan Masci, Luca M. Gambardella, and Jürgen Schmidhuber. 2011. Flexible, high performance convolutional neural networks for image classification. In Proceedings of the 22nd International Joint Conference on Artificial Intelligence—Volume Two (IJCAI’11). 1237--1242. Google Scholar
Digital Library
- Adam Coates, Brody Huval, Tao Wang, David Wu, Bryan Catanzaro, and Ng Andrew. 2013. Deep learning with COTS HPC systems. In Proceedings of the 30th International Conference on Machine Learning (ICML’13), Sanjoy Dasgupta and David Mcallester (Eds.), Vol. 28. JMLR Workshop and Conference Proceedings, 1337--1345. Google Scholar
Digital Library
- Maxwell D. Collins and Pushmeet Kohli. 2014. Memory bounded deep convolutional networks. CoRR abs/1412.1442 (2014).Google Scholar
- Henggang Cui, Hao Zhang, Gregory R. Ganger, Phillip B. Gibbons, and Eric P. Xing. 2016. GeePS: Scalable deep learning on distributed GPUs with a GPU-specialized parameter server. In Proceedings of the 11th European Conference on Computer Systems (EuroSys’16). ACM, New York, Article 4, 16 pages. Google Scholar
Digital Library
- Yann Le Cun, John S. Denker, and Sara A. Solla. 1990. Optimal brain damage. In Advances in Neural Information Processing Systems. Morgan Kaufmann, 598--605. Google Scholar
Digital Library
- O. E. David and N. S. Netanyahu. 2015. DeepSign: Deep learning for automatic malware signature generation and classification. In Proceedings of the 2015 International Joint Conference on Neural Networks (IJCNN’15). 1--8.Google Scholar
- S. Dreyfus. 1973. The computational solution of optimal control problems with time lag. IEEE Trans. Automat. Control 18, 4 (1973), 383--385.Google Scholar
Cross Ref
- Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. 2010. Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11 (2010), 625--660. Google Scholar
Digital Library
- Y. Gao, N. Zhang, H. Wang, X. Ding, X. Ye, G. Chen, and Y. Cao. 2016. iHear food: Eating detection using commodity bluetooth headsets. In Proceedings of the 2016 IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE’16). 163--172.Google Scholar
- V. Gokhale, J. Jin, A. Dundar, B. Martini, and E. Culurciello. 2014. A 240 G-ops/s mobile coprocessor for deep neural networks. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops. 696--701. Google Scholar
Digital Library
- Yunchao Gong, Liu Liu, Ming Yang, and Lubomir D. Bourdev. 2014. Compressing deep convolutional networks using vector quantization. CoRR abs/1412.6115 (2014). Retrieved from http://arxiv.org/abs/1412.6115.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 2672--2680. Google Scholar
Digital Library
- Song Han, Huizi Mao, and William J. Dally. 2015. Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. CoRR abs/1510.00149 (2015). http://arxiv.org/abs/1510.00149Google Scholar
Digital Library
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16).Google Scholar
Cross Ref
- Donald O. Hebb. 1949. The Organization of Behavior: A Neuropsychological Theory. Wiley.Google Scholar
- Geoffrey E. Hinton, Simon Osindero, and Yee-Whye Teh. 2006. A fast learning algorithm for deep belief nets. Neural Comput. 18, 7 (2006), 1527--1554. Google Scholar
Digital Library
- S. Hochreiter. 1991. Untersuchungen zu dynamischen neuronalen Netzen. Diploma thesis, Institut für Informatik, Lehrstuhl Prof. Brauer, Technische Universität München (1991).Google Scholar
- Sepp Hochreiter, Yoshua Bengio, Paolo Frasconi, and Jrgen Schmidhuber. 2001. Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies (2001).Google Scholar
- S. Hou, A. Saas, L. Chen, and Y. Ye. 2016. Deep4MalDroid: A deep learning framework for android malware detection based on linux kernel system call graphs. In Proceedings of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence Workshops (WIW’16). 104--111.Google Scholar
- Loc Nguyen Huynh, Rajesh Krishna Balan, and Youngki Lee. 2016. DeepSense: A GPU-based deep convolutional neural network framework on commodity mobile devices. In Proceedings of the 2016 Workshop on Wearable Systems and Applications (WearSys’16). ACM, New York, 25--30. Google Scholar
Digital Library
- IBM Corporation. 2016. Introducing A Brain-inspired Computer and an End-to-End Ecosystem that Could Revolutionize Computing. Retrieved from http://www.research.ibm.com/articles/Brain-chip.shtml (2016).Google Scholar
- Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22Nd ACM International Conference on Multimedia (MM’14). ACM, New York, 675--678. Google Scholar
Digital Library
- V. Jindal. 2016. Integrating mobile and cloud for PPG signal selection to monitor heart rate during intensive physical exercise. In Proceedings of the 2016 IEEE/ACM International Conference on Mobile Software Engineering and Systems (MOBILESoft’16). 36--37. Google Scholar
Digital Library
- Edward Kim, Miguel Corte-Real, and Zubair Baloch. 2016. A deep semantic mobile application for thyroid cytopathology (2016).Google Scholar
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25, P. Bartlett, F.c.n. Pereira, C.j.c. Burges, L. Bottou, and K.q. Weinberger (Eds.). 1106--1114. Retrieved from http://books.nips.cc/papers/files/nips25/NIPS2012_0534.pdf. Google Scholar
Digital Library
- P. Kuhad, A. Yassine, and S. Shimohammadi. 2015. Using distance estimation and deep learning to simplify calibration in food calorie measurement. In Proceedings of the 2015 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA’15). 1--6.Google Scholar
- G. Lacey, G. W. Taylor, and S. Areibi. 2016. Deep learning on FPGAs: Past, present, and future. ArXiv e-prints (Feb. 2016). arXiv:cs.DC/1602.04283.Google Scholar
- N. D. Lane, S. Bhattacharya, P. Georgiev, C. Forlivesi, L. Jiao, L. Qendro, and F. Kawsar. 2016. DeepX: A software accelerator for low-power deep learning inference on mobile devices. In Proceedings of the 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN’16). 1--12. Google Scholar
Digital Library
- Nicholas D. Lane, Sourav Bhattacharya, Petko Georgiev, Claudio Forlivesi, and Fahim Kawsar. 2015. An early resource characterization of deep learning on wearables, smartphones and internet-of-things devices. In Proceedings of the 2015 International Workshop on Internet of Things Towards Applications (IoT-App’15). ACM, New York, 7--12. Google Scholar
Digital Library
- Nicholas D. Lane and Petko Georgiev. 2015a. Can deep learning revolutionize mobile sensing? In Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications (HotMobile’15). 117--122. Retrieved from Google Scholar
Digital Library
- Nicholas D. Lane and Petko Georgiev. 2015b. Can deep learning revolutionize mobile sensing? In Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications (HotMobile’15). ACM, New York, 117--122. Google Scholar
Digital Library
- Nicholas D. Lane, Petko Georgiev, and Lorena Qendro. 2015. DeepEar: Robust smartphone audio sensing in unconstrained acoustic environments using deep learning. In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp’15). ACM, New York, 283--294. Google Scholar
Digital Library
- Seyyed Salar Latifi Oskouei, Hossein Golestani, Matin Hashemi, and Soheil Ghiasi. 2016. CNNdroid: GPU-accelerated execution of trained deep convolutional neural networks on android. In Proceedings of the 2016 ACM on Multimedia Conference (MM’16). ACM, New York, 1201--1205. Google Scholar
Digital Library
- Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. 1989. Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 4 (1989), 541--551. Google Scholar
Digital Library
- Jemin Lee, Jinse Kwon, and Hyungshin Kim. 2016. Reducing distraction of smartwatch users with deep learning. In Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services Adjunct (MobileHCI’16). ACM, New York, 948--953. Google Scholar
Digital Library
- Sicong Liu and Junzhao Du. 2016. Poster: MobiEar-building an environment-independent acoustic sensing platform for the deaf using deep learning. In Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services Companion (MobiSys’16 Companion). ACM, New York, 50--50. Google Scholar
Digital Library
- Warren S. McCulloch and Walter Pitts. 1943. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 4 (1943), 115--133.Google Scholar
Cross Ref
- Ian McGraw, Rohit Prabhavalkar, Raziel Alvarez, Montse Gonzalez Arenas, Kanishka Rao, David Rybach, Ouais Alsharif, Hasim Sak, Alexander Gruenstein, Franoise Beaufays, and Carolina Parada. 2016. Personalized speech recognition on mobile devices. In Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP’16).Google Scholar
Digital Library
- Michele Merler, Hui Wu, Rosario Uceda-Sosa, Quoc-Bao Nguyen, and John R. Smith. 2016. Snap, eat, RepEat: A food recognition engine for dietary logging. In Proceedings of the 2Nd International Workshop on Multimedia Assisted Dietary Management (MADiMa’16). ACM, New York, 31--40. Google Scholar
Digital Library
- Gaurav Mittal, Kaushal B. Yagnik, Mohit Garg, and Narayanan C. Krishnan. 2016. SpotGarbage: Smartphone app to detect garbage using deep learning. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp’16). ACM, New York, 940--945. Google Scholar
Digital Library
- S.-M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard. 2016. Deepfool: A simple and accurate method to fool deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2574--2582.Google Scholar
- Matthew W. Moskewicz, Forrest N. Iandola, and Kurt Keutzer. 2016. Boda-RTC: Productive generation of portable, efficient code for convolutional neural networks on mobile computing platforms. CoRR abs/1606.00094 (2016). Retrieved from http://arxiv.org/abs/1606.00094.Google Scholar
- Movidius. 2017. Embedded Neural Network Compute Framework: Fathom. Retrieved from https://www.movidius.com/solutions/machine-vision-algorithms/machine-learning (2017).Google Scholar
- Kumpati S. Narendra, Senior Member, and M. A. L. Thathachar. 1974. Learning automata—A survey. IEEE Trans. Syst. Man. Cybernet. (1974), 323--334.Google Scholar
Cross Ref
- NVIDIA. 2017. Next-Gen Smartphones, Tablets, Devices. Retrieved from http://www.nvidia.com/object/tegra-phones-tablet s.html (2017).Google Scholar
- NVIDIA Corporation. 2017. Embedded Systems Developer Kits 8 Modules. Retrieved from http://www.nvidia.com/object/embedded-systems-dev-kits-modules.html (2017).Google Scholar
- Nvidia, CUDA. 2010. Programming guide (2010).Google Scholar
- Sri Vijay Bharat Peddi, Pallavi Kuhad, Abdulsalam Yassine, Parisa Pouladzadeh, Shervin Shirmohammadi, and Ali Asghar Nazari Shirehjini. 2017. An intelligent cloud-based data processing broker for mobile e-health multimedia applications. Future Gen. Comput. Syst. 66 (2017), 71--86.Google Scholar
Cross Ref
- Pai Peng, Hongxiang Chen, Lidan Shou, Ke Chen, Gang Chen, and Chang Xu. 2015. DeepCamera: A unified framework for recognizing places-of-interest based on deep ConvNets. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management (CIKM’15). ACM, New York, 1891--1894. Google Scholar
Digital Library
- Qualcomm Technologies, Inc. 2016. Qualcomm Helps Make Your Mobile Devices Smarter With New Snapdragon Machine Learning Software Development Kit. Retrieved from https://www.qualcomm.com/news/releases/2016/05/02/qualcomm-helps-make-your-mobile-devices-smarter-new-snapdragon-machine (2016).Google Scholar
- Rajat Raina, Anand Madhavan, and Andrew Y. Ng. 2009. Large-scale deep unsupervised learning using graphics processors. In Proceedings of the 26th Annual International Conference on Machine Learning (ICML’09). 873--880. Google Scholar
Digital Library
- R. Reed. Pruning algorithms-A survey. Trans. Neur. Netw. 4, 5, 740--747. Google Scholar
Digital Library
- F. Rosenblatt. 1958. The perceptron: A probabilistic model for information storage and organization in the brain. Psychol. Rev. (1958), 65--386.Google Scholar
- F. Rosenblatt. 1962. Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Spartan Books.Google Scholar
- David E. Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams. 1986. Learning internal representations by error propagation. In Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume 1: Foundations, David E. Rumelhart and James L. Mcclelland (Eds.). MIT Press, Cambridge, MA, 318--362. Google Scholar
Digital Library
- Jason Sanders and Edward Kandrot. 2010. CUDA by Example: An Introduction to General-Purpose GPU Programming, Portable Documents. Addison-Wesley Professional. Google Scholar
Digital Library
- M. Sharif, S. Bhagavatula, L. Bauer, and M. K. Reiter. 2016. Accessorize to a crime: Real and stealthy attacks on state-ofthe-art face recognition. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. 1528--1540. Google Scholar
Digital Library
- Vikas Sindhwani, Tara Sainath, and Sanjiv Kumar. 2015. Structured transforms for small-footprint deep learning. In Advances in Neural Information Processing Systems 28, C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett (Eds.). Curran Associates, Inc., 3088--3096. Google Scholar
Digital Library
- Guillaume Soulié, Vincent Gripon, and Maëlys Robert. 2016. Compression of Deep Neural Networks on the Fly. Springer International Publishing, 153--160.Google Scholar
- Slawomir W. Stepniewski and Andy J. Keane. 1997. Pruning backpropagation neural networks using modern stochastic optimisation techniques. Neural Comput. Applic. 5, 2 (1997), 76--98.Google Scholar
Cross Ref
- Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS’14). MIT Press, Cambridge, MA, 3104--3112. Retrieved from http://dl.acm.org/citation.cfm?id=2969033.2969173 Google Scholar
Digital Library
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going deeper with convolutions. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR’15).Google Scholar
Cross Ref
- C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus. 2014. Intriguing properties of neural networks. In Proceedings of the International Conference on Learning Representations.Google Scholar
- Ryosuke Tanno, Koichi Okamoto, and Keiji Yanai. 2016. DeepFoodCam: A DCNN-based real-time mobile food recognition system. In Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management (MADiMa’16). ACM, New York, 89--89. Google Scholar
Digital Library
- Vladimir N. Vapnik. 1995. The Nature of Statistical Learning Theory. Springer-Verlag New York, Inc., New York. Google Scholar
Digital Library
- Pascal Vincent, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol. 2008. Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th International Conference on Machine Learning (ICML’08). 1096--1103. Google Scholar
Digital Library
- Joel Emer Vivienne Sze. 2016. Chip could bring deep learning to mobile devices. Retrieved from http://www.eurekalert.org/pub_releases/2016-02/m iot-ccb020316.php (2016).Google Scholar
- Saiwen Wang, Jie Song, Jaime Lien, Ivan Poupyrev, and Otmar Hilliges. 2016. Interacting with soli: Exploring fine-grained dynamic gesture recognition in the radio-frequency spectrum. In Proceedings of the 29th Annual Symposium on User Interface Software and Technology (UIST’16). ACM, New York, 851--860. Google Scholar
Digital Library
- Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. 2016. Learning structured sparsity in deep neural networks. CoRR abs/1608.03665 (2016).Google Scholar
- J. Weng, N. Ahuja, and T. S. Huang. 1992. Cresceptron: A self-organizing neural network which grows adaptively. In Proceedings of the 1992 IJCNN International Joint Conference on Neural Networks, Vol. 1. 576--581.Google Scholar
- Paul J. Werbos. 1982. Applications of Advances in Nonlinear Sensitivity Analysis. Springer, Berlin . 762--770.Google Scholar
- Bernard Widrow and Marcian E. Hoff. 1962. Associative Storage and Retrieval of Digital Information in Networks of Adaptive “Neurons.” Springer, Boston, MA, 160--160.Google Scholar
- Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, and Jian Cheng. 2016a. Quantized convolutional neural networks for mobile devices. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). 4820--4828.Google Scholar
Cross Ref
- Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, and et al. 2016b. Google’s neural machine translation system: Bridging the gap between human and machine translation. CoRR abs/1609.08144 (2016). Retrieved from http://arxiv.org/abs/1609.08144.Google Scholar
- Zhenlong Yuan, Yongqiang Lu, Zhaoguo Wang, and Yibo Xue. 2014. Droid-sec: Deep learning in android malware detection. SIGCOMM Comput. Commun. Rev. 44, 4 (Aug. 2014), 371--372. Google Scholar
Digital Library
- Z. Yuan, Y. Lu, and Y. Xue. 2016. Droiddetector: Android malware characterization and detection using deep learning. Tsinghua Sci. Technol. 21, 1 (Feb. 2016), 114--123.Google Scholar
- Matthew D. Zeiler and Rob Fergus. 2014. Visualizing and Understanding Convolutional Networks. Springer International Publishing, 818--833.Google Scholar
- Q. Zhang, H. Li, Z. Sun, Z. He, and T. Tan. 2016. Exploring complementary features for iris recognition on mobile devices. In Proceedings of the 2016 International Conference on Biometrics (ICB’16). 1--8.Google Scholar
- Sixin Zhang, Anna E. Choromanska, and Yann LeCun. 2015. Deep learning with elastic averaging SGD. In Advances in Neural Information Processing Systems 28, C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett (Eds.). Curran Associates, Inc., 685--693. Google Scholar
Digital Library
- J. Zhu, A. Pande, P. Mohapatra, and J. J. Han. 2015. Using deep learning for energy expenditure estimation with wearable sensors. In Proceedings of the 2015 17th International Conference on E-health Networking, Application Services (HealthCom’15). 501--506.Google Scholar
Index Terms
Deep Learning for Mobile Multimedia: A Survey
Recommendations
Deep Learning on Mobile and Embedded Devices: State-of-the-art, Challenges, and Future Directions
Recent years have witnessed an exponential increase in the use of mobile and embedded devices. With the great success of deep learning in many fields, there is an emerging trend to deploy deep learning on mobile and embedded devices to better meet the ...
Deep Learning: Methods and Applications
This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. The application areas are chosen with the following three criteria in mind: (1) expertise or knowledge ...
Mobile Sensing Through Deep Learning
Ph.D. Forum '17: Proceedings of the 2017 Workshop on MobiSys 2017 Ph.D. ForumToday, mobile devices are equipped with powerful processors along with various on-device sensors. Over the past few years, deep learning has become the dominant approach in the field of machine learning due to its impressive performance. We envision ...






Comments