cs249r_book/contents/efficient_ai/efficient_ai.bib

@book{barroso2019datacenter,
 author = {Barroso, Luiz Andr\'e and H\"olzle, Urs and Ranganathan, Parthasarathy},
 doi = {10.1007/978-3-031-01761-2},
 isbn = {9783031006333, 9783031017612},
 issn = {1935-3235, 1935-3243},
 publisher = {Springer International Publishing},
 source = {Crossref},
 subtitle = {Designing Warehouse-Scale Machines},
 title = {The Datacenter as a Computer},
 url = {https://doi.org/10.1007/978-3-031-01761-2},
 year = {2019}
}

@article{chowdhery2019visual,
 author = {Chowdhery, Aakanksha and Warden, Pete and Shlens, Jonathon and Howard, Andrew and Rhodes, Rocky},
 journal = {arXiv preprint arXiv:1906.05721},
 title = {Visual wake words dataset},
 year = {2019}
}

@misc{han2016deep,
 archiveprefix = {arXiv},
 author = {Han, Song and Mao, Huizi and Dally, William J.},
 eprint = {1510.00149},
 primaryclass = {cs.CV},
 title = {Deep Compression: {Compressing} Deep Neural Networks with Pruning, Trained Quantization and {Huffman} Coding},
 year = {2016}
}

@inproceedings{he2016deep,
 author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/cvpr/HeZRS16.bib},
 booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2016, Las Vegas, NV, USA, June 27-30, 2016},
 doi = {10.1109/CVPR.2016.90},
 pages = {770--778},
 publisher = {{IEEE} Computer Society},
 timestamp = {Wed, 17 Apr 2019 01:00:00 +0200},
 title = {Deep Residual Learning for Image Recognition},
 url = {https://doi.org/10.1109/CVPR.2016.90},
 year = {2016}
}

@misc{howard2017mobilenets,
 author = {Howard, Andrew G. and Zhu, Menglong and Chen, Bo and Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and Andreetto, Marco and Adam, Hartwig},
 journal = {ArXiv preprint},
 title = {{MobileNets:} {Efficient} Convolutional Neural Networks for Mobile Vision Applications},
 url = {https://arxiv.org/abs/1704.04861},
 volume = {abs/1704.04861},
 year = {2017}
}

@inproceedings{hu2018squeeze,
 author = {Hu, Jie and Shen, Li and Sun, Gang},
 booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
 pages = {7132--7141},
 title = {Squeeze-and-excitation networks},
 year = {2018}
}

@article{iandola2016squeezenet,
 author = {Iandola, Forrest N and Han, Song and Moskewicz, Matthew W and Ashraf, Khalid and Dally, William J and Keutzer, Kurt},
 journal = {ArXiv preprint},
 title = {{SqueezeNet:} {Alexnet-level} accuracy with 50x fewer parameters and 0.5 {MB} model size},
 url = {https://arxiv.org/abs/1602.07360},
 volume = {abs/1602.07360},
 year = {2016}
}

@inproceedings{jouppi2017datacenter,
 abstract = {Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC{\textemdash}called a Tensor Processing Unit (TPU) {\textemdash} deployed in datacenters since 2015 that accelerates the inference phase of neural networks (NN). The heart of the TPU is a 65,536 8-bit MAC matrix multiply unit that offers a peak throughput of 92 TeraOps/second (TOPS) and a large (28 MiB) software-managed on-chip memory. The TPU's deterministic execution model is a better match to the 99th-percentile response-time requirement of our NN applications than are the time-varying optimizations of CPUs and GPUs that help average throughput more than guaranteed latency. The lack of such features helps explain why, despite having myriad MACs and a big memory, the TPU is relatively small and low power. We compare the TPU to a server-class Intel Haswell CPU and an Nvidia K80 GPU, which are contemporaries deployed in the same datacenters. Our workload, written in the high-level TensorFlow framework, uses production NN applications (MLPs, CNNs, and LSTMs) that represent 95\% of our datacenters' NN inference demand. Despite low utilization for some applications, the TPU is on average about 15X {\textendash} 30X faster than its contemporary GPU or CPU, with TOPS/Watt about 30X {\textendash} 80X higher. Moreover, using the CPU's GDDR5 memory in the TPU would triple achieved TOPS and raise TOPS/Watt to nearly 70X the GPU and 200X the CPU.},
 address = {New York, NY, USA},
 author = {Jouppi, Norman P. and Young, Cliff and Patil, Nishant and Patterson, David and Agrawal, Gaurav and Bajwa, Raminder and Bates, Sarah and Bhatia, Suresh and Boden, Nan and Borchers, Al and Boyle, Rick and Cantin, Pierre-luc and Chao, Clifford and Clark, Chris and Coriell, Jeremy and Daley, Mike and Dau, Matt and Dean, Jeffrey and Gelb, Ben and Ghaemmaghami, Tara Vazir and Gottipati, Rajendra and Gulland, William and Hagmann, Robert and Ho, C. Richard and Hogberg, Doug and Hu, John and Hundt, Robert and Hurt, Dan and Ibarz, Julian and Jaffey, Aaron and Jaworski, Alek and Kaplan, Alexander and Khaitan, Harshit and Killebrew, Daniel and Koch, Andy and Kumar, Naveen and Lacy, Steve and Laudon, James and Law, James and Le, Diemthu and Leary, Chris and Liu, Zhuyuan and Lucke, Kyle and Lundin, Alan and MacKean, Gordon and Maggiore, Adriana and Mahony, Maire and Miller, Kieran and Nagarajan, Rahul and Narayanaswami, Ravi and Ni, Ray and Nix, Kathy and Norrie, Thomas and Omernick, Mark and Penukonda, Narayana and Phelps, Andy and Ross, Jonathan and Ross, Matt and Salek, Amir and Samadiani, Emad and Severn, Chris and Sizikov, Gregory and Snelham, Matthew and Souter, Jed and Steinberg, Dan and Swing, Andy and Tan, Mercedes and Thorson, Gregory and Tian, Bo and Toma, Horia and Tuttle, Erick and Vasudevan, Vijay and Walter, Richard and Wang, Walter and Wilcox, Eric and Yoon, Doe Hyun},
 bdsk-url-1 = {https://doi.org/10.1145/3079856.3080246},
 booktitle = {Proceedings of the 44th Annual International Symposium on Computer Architecture},
 doi = {10.1145/3079856.3080246},
 isbn = {9781450348928},
 keywords = {accelerator, neural network, MLP, TPU, CNN, deep learning, domain-specific architecture, GPU, TensorFlow, DNN, RNN, LSTM},
 location = {Toronto, ON, Canada},
 numpages = {12},
 pages = {1--12},
 publisher = {ACM},
 series = {ISCA '17},
 source = {Crossref},
 title = {In-Datacenter Performance Analysis of a Tensor Processing Unit},
 url = {https://doi.org/10.1145/3079856.3080246},
 year = {2017}
}

@article{lecun1989optimal,
 author = {LeCun, Yann and Denker, John and Solla, Sara},
 journal = {Adv Neural Inf Process Syst},
 title = {Optimal brain damage},
 volume = {2},
 year = {1989}
}

@article{li2019edge,
 author = {Li, En and Zeng, Liekang and Zhou, Zhi and Chen, Xu},
 doi = {10.1109/twc.2019.2946140},
 issn = {1536-1276, 1558-2248},
 journal = {IEEE Trans. Wireless Commun.},
 number = {1},
 pages = {447--457},
 publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
 source = {Crossref},
 title = {Edge {AI:} {On-demand} Accelerating Deep Neural Network Inference via Edge Computing},
 url = {https://doi.org/10.1109/twc.2019.2946140},
 volume = {19},
 year = {2020}
}

@inproceedings{lin2014microsoft,
 author = {Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
 booktitle = {Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13},
 organization = {Springer},
 pages = {740--755},
 title = {Microsoft coco: Common objects in context},
 year = {2014}
}

@article{russakovsky2015imagenet,
 author = {Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael and others},
 journal = {International journal of computer vision},
 pages = {211--252},
 publisher = {Springer},
 title = {Imagenet large scale visual recognition challenge},
 volume = {115},
 year = {2015}
}

@article{schizas2022tinyml,
  author        = {Schizas, Nikolaos and Karras, Aristeidis and Karras, Christos and Sioutas, Spyros},
  journal       = {Future Internet},
  title         = {TinyML for Ultra-Low Power AI and Large Scale IoT Deployments: A Systematic Review},
  doi           = {https://doi.org/10.3390/fi14120363},
  year          = {2022}
}

@article{warden2018speech,
 author = {Warden, Pete},
 journal = {arXiv preprint arXiv:1804.03209},
 title = {Speech commands: A dataset for limited-vocabulary speech recognition},
 year = {2018}
}

@book{warden2019tinyml,
 author = {Warden, Pete and Situnayake, Daniel},
 publisher = {O'Reilly Media},
 title = {Tinyml: {Machine} learning with tensorflow lite on arduino and ultra-low-power microcontrollers},
 year = {2019}
}

@inproceedings{xie2017aggregated,
 author = {Xie, Saining and Girshick, Ross and Doll{\'a}r, Piotr and Tu, Zhuowen and He, Kaiming},
 booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
 pages = {1492--1500},
 title = {Aggregated residual transformations for deep neural networks},
 year = {2017}
}