mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-05-04 00:29:10 -05:00
2867c9038f
Improved citation key for bibtex: Added a script to automatically generate and update citation keys in QMD files. This resolves formatting issues caused by characters like underscores in the original citation keys.
92 lines
6.7 KiB
BibTeX
92 lines
6.7 KiB
BibTeX
@article{bank2023autoencoders,
|
|
author = {Bank, Dor and Koenigstein, Noam and Giryes, Raja},
|
|
journal = {Machine Learning for Data Science Handbook: Data Mining and Knowledge Discovery Handbook},
|
|
pages = {353--374},
|
|
publisher = {Springer},
|
|
title = {Autoencoders},
|
|
year = {2023}
|
|
}
|
|
|
|
@article{goodfellow2020generative,
|
|
author = {Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
|
|
doi = {10.1145/3422622},
|
|
issn = {0001-0782, 1557-7317},
|
|
journal = {Commun. ACM},
|
|
number = {11},
|
|
pages = {139--144},
|
|
publisher = {Association for Computing Machinery (ACM)},
|
|
source = {Crossref},
|
|
title = {Generative adversarial networks},
|
|
url = {https://doi.org/10.1145/3422622},
|
|
volume = {63},
|
|
year = {2020}
|
|
}
|
|
|
|
@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}
|
|
}
|
|
|
|
@inproceedings{krizhevsky2012imagenet,
|
|
author = {Alex Krizhevsky and Ilya Sutskever and Geoffrey E. Hinton},
|
|
bibsource = {dblp computer science bibliography, https://dblp.org},
|
|
biburl = {https://dblp.org/rec/conf/nips/KrizhevskySH12.bib},
|
|
booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States},
|
|
editor = {Peter L. Bartlett and Fernando C. N. Pereira and Christopher J. C. Burges and L{\'{e}}on Bottou and Kilian Q. Weinberger},
|
|
pages = {1106--1114},
|
|
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
|
|
title = {ImageNet Classification with Deep Convolutional Neural Networks},
|
|
url = {https://proceedings.neurips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html},
|
|
year = {2012}
|
|
}
|
|
|
|
@book{rosenblatt1957perceptron,
|
|
author = {Rosenblatt, Frank},
|
|
publisher = {Cornell Aeronautical Laboratory},
|
|
title = {The perceptron, a perceiving and recognizing automaton Project Para},
|
|
year = {1957}
|
|
}
|
|
|
|
@article{rumelhart1986learning,
|
|
author = {Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.},
|
|
doi = {10.1038/323533a0},
|
|
issn = {0028-0836, 1476-4687},
|
|
journal = {Nature},
|
|
number = {6088},
|
|
pages = {533--536},
|
|
publisher = {Springer Science and Business Media LLC},
|
|
source = {Crossref},
|
|
title = {Learning representations by back-propagating errors},
|
|
url = {https://doi.org/10.1038/323533a0},
|
|
volume = {323},
|
|
year = {1986}
|
|
}
|
|
|
|
@inproceedings{vaswani2017attention,
|
|
author = {Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin},
|
|
bibsource = {dblp computer science bibliography, https://dblp.org},
|
|
biburl = {https://dblp.org/rec/conf/nips/VaswaniSPUJGKP17.bib},
|
|
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}},
|
|
editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett},
|
|
pages = {5998--6008},
|
|
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
|
|
title = {Attention is All you Need},
|
|
url = {https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html},
|
|
year = {2017}
|
|
}
|