低複雜度卷積神經網路訓練與其低功耗運算單元電路設計

林柏成

doi:10.6342/NTU201704424

山西大学，您好！

感谢采购，人社期刊库｜人社论文库，期间：2025/01/01~2025/12/31

感谢试用，科学期刊库｜科学论文库，期间：2024/10/20~2025/01/20

浏览高级检索

关闭
检索检索高级检索出版物检索
浏览期刊主题浏览核心期刊浏览期刊拼音浏览

关闭

查询符号(半角)	查询符号意义说明
空格	表示为「AND」两个查询词之交集
双引号 ( " " )	片语以双引号标示开始及结束，而且只寻找出现顺序相同的字词，例： " image process "
?	表示一个字母切截，输入两个?表两个字母，依此类推，例：输入「Appl?」，查得结果应为appl e , appl y … ( 常用于英文字查询 )
*	表示不限字母切截，由0~n. 例：输入「appl*」，查得结果应为appl e , appl es , appl y , appl ied , appl ication … ( 常用于英文字查询 )
AND、OR、NOT	布尔逻辑组合关键字，用来扩大或缩小查询范围的技巧。 (1) AND ：缩小查询范围 (2) OR ：扩大查询范围(3) NOT：排除不相关的范围

DOI 是数位物件识别码（ D igital O bject I dentifier ）的简称，
为物件在网路上的唯一识别码，可用于永久连结并引用目标物件。

使用DOI作为永久连结

每个DOI号前面加上「 http://dx.doi.org/ 」便成为永久网址。
如以DOI号为 10.5297/ser.1201.002 的文献为例，此文献的永久连结便是： http://dx.doi.org/ 10.5297/ser.1201.002 。
日后不论出版单位如何更动此文献位置，永久连结所指向的位置皆会即时更新，不再错失重要的研究。

引用含有DOI的文献

有DOI的文献在引用时皆应同时引用DOI。若使用APA、Chicago以外未规范DOI的引用格式，可引用DOI永久连结。

DOI可强化引用精确性、增强学术圈连结，并给予使用者跨平台的良好使用经验，目前在全世界已有超过五千万个对象申请DOI。如想对DOI的使用与概念有进一步了解，请参考（）。

书目管理工具

相关连结

问题回报

全文下载

低复杂度卷积神经网路训练与其低功耗运算单元电路设计

Low-complexity Convolution Neural Network Training and Low Power Circuit Design of its Processing Element

林柏成 , 硕士　　导师：阙志达　　

繁体中文 DOI： 10.6342/NTU201704424

深度神经网路；卷积神经网路；量化； ImageNet ； deep neural network ； convolution neural network ； quantization ； ImageNet

0 个人觉得这篇文章赞

摘要 │ 参考文献 (45) │ 国际计量

摘要〈TOP〉

并列摘要〈TOP〉

In recent years, deep neural networks and AI research had attracted much attention. There are several types of neural networks, including multilayer perceptron (MLP), convolution neural network (CNN), recurrent neural network (RNN). Among these architectures, convolution neural network had been widely used in image processing task including, but not limited to image classification, object detection, natural language processing, even GO games. Recently, it has been showed that CNN can be built with hundreds of layers in order to solve tough tasks, however, at the same time require much more computing effort compare to traditional MLP.
	Convolution neural network can be trained by iteratively passing training data forward through network, passing output error backward through network, adjusting weight of network, traversing on the loss surface to get to the global minimum for the best model. With the trained model, one can pass the data through the network once and get the inference result.
We introduced the Floating-point signed digit (FloatSD) algorithm for training and inference phase of CNN to reduced computational effort. In addition, we quantize the neuron output of each layer and the backward delta error for more computational saving. We show that it's not necessary to use 32 bit floating point at training phase in order to get similar results.
We implement our FloatSD and quantizing algorithms by modifying the source code of the well known deep learning framework called Caffe, developed by Berkeley Artificial Intelligence Research center. Three famous image classification dataset: MNIST, CIFAR-10, ImageNet are used throughout our experiments. Results show that we can get better result at MNIST and CIFAR-10 datasets. Even at ImageNet dataset, we are able to train from scratch by our proposed algorithm and obtain a 90%-top-5-accuracy model and get only 0.8% degradation of top-5 accuracy.
In addition to software simulation, we also design the circuit of processing element of FloatSD, which will be the computational module of our on-going general purpose neural network chip. Using FloatSD algorithm, clock gating, zero-sorting technique, our circuit area and power consumption is 16.6% and 0.72% to 10.7% of floating point version respectively compared with 32bit floating point counterpart.

参考文献 ( 45 ) 〈TOP〉

[1] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Advances in Neural Information Processing Systems, 2012, pp. 1097–1105.
连结：
[2] G. Hinton, L. Deng, D. Yu, G. E. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath, et al. “Deep neural networks for acoustic modeling in speech recognition,” IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 82-97, 2012
连结：
[4] D. Silver et al., “Mastering the game of Go with deep neural networks and tree search,” Nature, vol. 529, no. 7587, pp. 484–489, Jan. 2016.
连结：
[7] P. Norman. et al, “In-Datacenter Performance Analysis of a Tensor Processing Unit TM,” ArXiv:1704.04760v1 [cs.AR], 2017.
连结：
[9] Y. Chen, T. Luo, S. Liu, S. Zhang, L. He, J. Wang, L. Li, T. Chen, Z. Xu, N. Sun, O. Temam, "DaDianNao: A machine-learning supercomputer," in Proc. of 2014 47th Annual IEEE/ACM International Symposium on MICRO, Dec 2014, pp. 609-622.
连结：

国际计量

〈TOP〉

E-mail ：

文章公开取用时，将寄通知信至您填写的信箱地址

E-mail ：

使用DOI作为永久连结

引用含有DOI的文献

DOI可强化引用精确性、增强学术圈连结，并给予使用者跨平台的良好使用经验，目前在全世界已有超过五千万个对象申请DOI。 如想对DOI的使用与概念有进一步了解，请参考 （ ） 。

DOI可强化引用精确性、增强学术圈连结，并给予使用者跨平台的良好使用经验，目前在全世界已有超过五千万个对象申请DOI。如想对DOI的使用与概念有进一步了解，请参考（）。