請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/21896完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 徐慰中 | |
| dc.contributor.author | Chien-Ping Chin | en |
| dc.contributor.author | 秦建平 | zh_TW |
| dc.date.accessioned | 2021-06-08T03:51:58Z | - |
| dc.date.copyright | 2018-08-21 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-08-20 | |
| dc.identifier.citation | [1] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel, and Baird H. S. Constrained neural network for unconstrained handwritten digit recognition. In C Suen, editor, Frontiers in Handwriting Recognition, Montreal, 1990. CENPARMI, Concordia University.
[2] ChristianSzegedy,WeiLiu,YangqingJia,PierreSermanet,ScottE.Reed,Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. Going deeper with convolutions. CoRR, abs/1409.4842, 2014. [3] Awni Y. Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, and An- drew Y. Ng. Deep speech: Scaling up end-to-end speech recognition. CoRR, abs/ 1412.5567, 2014. [4] David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driess- che, Thore Graepel, and Demis Hassabis. Mastering the game of go without human knowledge. Nature, 550:354 EP –, 10 2017. [5] Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. A neural algorithm of artistic style. CoRR, abs/1508.06576, 2015. [6] AndrewG.Howard,MenglongZhu,BoChen,DmitryKalenichenko,WeijunWang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. Mobilenets: Efficient con-volutional neural networks for mobile vision applications. CoRR, abs/1704.04861, 2017. [7] Forrest N. Iandola, Matthew W. Moskewicz, Khalid Ashraf, Song Han, William J. Dally, and Kurt Keutzer. Squeezenet: Alexnet-level accuracy with 50x fewer pa- rameters and <1mb model size. CoRR, abs/1602.07360, 2016. [8] XiangyuZhang,XinyuZhou,MengxiaoLin,andJianSun.Shufflenet:Anextremely efficient convolutional neural network for mobile devices. CoRR, abs/1707.01083, 2017. [9] Gao Huang, Zhuang Liu, and Kilian Q. Weinberger. Densely connected convolu- tional networks. CoRR, abs/1608.06993, 2016. [10] Fengfu Li and Bin Liu. Ternary weight networks. CoRR, abs/1605.04711, 2016. [11] Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. Binaryconnect: Training deep neural networks with binary weights during propagations. CoRR, abs/ 1511.00363, 2015. [12] Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi. Xnor- net: Imagenet classification using binary convolutional neural networks. CoRR, abs/ 1603.05279, 2016. [13] Matthieu Courbariaux and Yoshua Bengio. Binarynet: Training deep neural net- works with weights and activations constrained to +1 or -1. CoRR, abs/1602.02830, 2016. [14] Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, An- drew G. Howard, Hartwig Adam, and Dmitry Kalenichenko. Quantization and train- ing of neural networks for efficient integer-arithmetic-only inference. CoRR, abs/ 1712.05877, 2017. [15] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In F. Pereira, C. J. C. Burges, L. Bottou,and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 25, pages 1097–1105. Curran Associates, Inc., 2012. [16] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. CoRR, abs/1512.03385, 2015. [17] Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghe- mawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dande- lion Mané, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. TensorFlow: Large- scale machine learning on heterogeneous systems, 2015. Software available from tensorflow.org. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/21896 | - |
| dc.description.abstract | 所謂的近似運算指的是對於一個問題，電腦根據一個近似的計算過 程給出結果。這篇論文主要是在研究近似運算如何減少類神經網路的 運算。論文首先對於近年討論如何加快類神經網路的研究做一個簡單 的介紹，接著對於這篇研究的主題–量化類神經網路的相關概念作介 紹。再來我們描述如何設計實驗來驗證量化模型對於類神經網路的影 響。最後我們介紹量化類神經網路如何應用在現實的問題並對這篇論 文作出總結。 | zh_TW |
| dc.description.abstract | This thesis gives a research on how approximate computing, which gives an imprecise computation, can reduce computation on neural network. We first give an overview of previous work on how to reduce computation of neural network, then we discuss the basic concept of quantized neural network. Next we describe how to design an experiment to investigate the influence of quantized model. Finally, we discuss how to apply quantized model to real world application. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-08T03:51:58Z (GMT). No. of bitstreams: 1 ntu-107-R03922119-1.pdf: 3231332 bytes, checksum: d21342920715fb5f797912bfac8e7494 (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 口試委員 i 謝 ii 中文 要 iii Abstract iv Contents v List of Figures viii List of Tables ix
1 Introduction 1 1.1 RelatedWorks................................ 1 1.2 MobileNet.................................. 2 1.3 SqueezeNet ................................. 2 1.4 ShuffleNet.................................. 2 1.5 BinaryConnect ............................... 4 1.6 XNOR-Net ................................. 4 1.7 TernaryWeightNetwork .......................... 4 1.8 Outline ................................... 5 2 Quantized Neural Network 6 2.1 LearningParadigm ............................. 6 2.1.1 SupervisedLearning ........................ 6 2.1.2 UnsupervisedLearning....................... 6 2.1.3 ReinforcementLearning ...................... 6 2.2 NeuralNetwork............................... 7 2.3 OverfittingofNeuralNetwork ....................... 8 2.4 GradientVanishofNeuralNetwork .................... 8 2.5 Quantization................................. 9 2.6 ApproximateComputing .......................... 9 2.7 StrategiesForQuantization......................... 10 2.7.1 FakeQuantization ......................... 10 2.7.2 UniformQuantization ....................... 10 2.7.3 Non-UniformQuantization..................... 11 3 Experiment 13 3.1 TensorFlow ................................. 13 3.2 NVIDIAGPU................................ 14 3.3 MNIST ................................... 14 3.4 CIFAR-10.................................. 14 3.5 Multi-LayerPerceptron........................... 14 3.6 ConvNet................................... 16 3.6.1 Convolution ............................ 16 3.6.2 MaxPooling ............................ 16 3.7 ResNet.................................... 16 3.8 ExperimentDesign ............................. 17 3.9 Evaluation.................................. 17 3.9.1 Accuracy .............................. 17 3.9.2 Speedup............................... 18 3.9.3 Tradeoff............................... 19 3.9.4 FurtherExtension:8-bitQuantization . . . . . . . . . . . . . . . 19 3.9.5 DoesQuantizationValuable?.................... 19 4 Conclusion.................... 21 Bibliography.................... 23 | |
| dc.language.iso | en | |
| dc.title | 量化類神經網路的近似運算 | zh_TW |
| dc.title | Approximate Computing with Quantized Neural Network | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 劉邦鋒,吳真貞 | |
| dc.subject.keyword | 機器學習,近似運算,量化類神經網路,深度學習, | zh_TW |
| dc.subject.keyword | Machine Learning,Approximate Computing,Quantized Neural Network,Deep Learning, | en |
| dc.relation.page | 25 | |
| dc.identifier.doi | 10.6342/NTU201803958 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2018-08-20 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-107-1.pdf 目前未授權公開取用 | 3.16 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。