[1]SHA Yun,LI Qifei,GAN Jianwang,et al.Application of PSdropout convolutional neural network in inspection car for hazardous chemicals[J].CAAI Transactions on Intelligent Systems,2020,15(6):1131-1139.[doi:10.11992/tis.202007022]
Copy
Application of PSdropout convolutional neural network in inspection car for hazardous chemicals
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
15
Number of periods:
2020 6
Page number:
1131-1139
Column:
学术论文—机器学习
Public date:
2020-11-05
- Title:
- Application of PSdropout convolutional neural network in inspection car for hazardous chemicals
- Keywords:
- storage of hazardous chemicals; inspection vehicle; convolutional neural network; dropout; Poisson distribution; subnetwork; full link layer; network architecture
- CLC:
- TP391.4;TQ086.5
- DOI:
- 10.11992/tis.202007022
- Abstract:
- The storage environment of hazardous chemicals is complex and changeable. To adapt to different environments, visual-inspection vehicles based on convolutional neural networks require fast training methods, but the problem of improving the training speed of convolutional neural networks remains to be solved. To improve the training speed of the algorithm, effective neural cell in network must be extracted from the network more quickly. In the traditional algorithm, the removal of neurons from the fully connected layer is typically performed using the dropout method, which is based on the Bernoulli distribution hypothesis. In this paper, we propose a dropout method based on the Poisson distribution. Theoretically, by making full use of the historical behavior of neurons, the maximum likelihood function based on the Poisson distribution is similar to that based on the Bernoulli distribution. The experimental results show that while maintaining the correct rate, the training can be converged in advance, thereby saving the training time.
- References:
-
[1] 刘学君, 江帆, 戴波, 等. 基于ARM的危化品仓库堆垛安全距离监测装置的研究与开发[J]. 制造业自动化, 2016, 38(4): 11-14, 25
LIU Xuejun, JIANG Fan, DAI Bo, et al. The research and development of stack safe distance monitoring device for the chemicals warehouse based on ARM[J]. Manufacturing automation, 2016, 38(4): 11-14, 25
[2] 李琳. 基于UWB定位的危化品仓库管理的设计和研究[D]. 北京: 北京邮电大学, 2018.
LI Lin. Design and research of hazardous chemicals warehouse management based on UWB positioning[D]. Beijing: Beijing University of Posts and Telecommunications, 2018.
[3] 戴波, 周泽彧, 张岩, 等. 危化品仓储堆垛安全距离监测系统设计[J]. 化工学报, 2019, 70(002): 707-715
DAI Bo, ZHOU Zeyu, ZHANG Yan, et al. Design of safe distance monitoring system for hazardous chemicals storage stack[J]. CIESC Journal, 2019, 70(002): 707-715
[4] 戴波, 吕昕, 刘学君, 等. 基于UWB四参考点矢量补偿的危化品仓储堆垛货物定位方法[J]. 化工学报, 2016, 67(3): 871-877
DAI Bo, Lü Xin, LIU Xuejun, et al. A UWB-based four reference vectors compensation method applied on hazardous chemicals warehouse stacking positioning[J]. CIESC journal, 2016, 67(3): 871-877
[5] DAI Bo, LI Yanfei, REN Haisheng, et al. Research on optimization for safe layout of hazardous chemicals warehouse based on genetic algorithm[J]. IFAC-PapersOnline, 2008, 51(18): 245-250.
[6] SRINIVAS S, BABU R V. Data-free parameter pruning for deep neural networks[C]//Proceedings of British Machine Vision Conference 2015. Swansea, UK, 2015: 1-12.
[7] HAN Song, POOL J, TRAN J, et al. Learning both weights and connections for efficient neural networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal, Quebec, Canada, 2015: 1135-1143.
[8] CHEN Wenlin, WILSON J, TYREE S, et al. Compressing neural networks with the hashing trick[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille, France, 2015: 2285-2294.
[9] HAN Song, MAO Huizi, DALLY W J. Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding[C]//Proceedings of 2016 International Conference on Learning Representations. San Juan, Pucrto Rico, 2015: 3-7.
[10] MA Rongrong, NIU Lingfeng. A survey of sparse-learning methods for deep neural networks[C]//Proceedings of 2018 IEEE/WIC/ACM International Conference on Web Intelligence. Santiago, Chile, 2018: 647-650.
[11] 李江昀, 赵义凯, 薛卓尔, 等. 深度神经网络模型压缩综述[J]. 工程科学学报, 2019, 41(10): 1229-1239
LI Jiangyun, ZHAO Yikai, XUE Zhuoer, et al. A survey of model compression for deep neural networks[J]. Chinese journal of engineering, 2019, 41(10): 1229-1239
[12] 纪荣嵘, 林绍辉, 晁飞, 等. 深度神经网络压缩与加速综述[J]. 计算机研究与发展, 2018, 55(9): 1871-1888
JI Rongrong, LIN Shaohui, CHAO Fei, et al. Deep neural network compression and acceleration: a review[J]. Journal of computer research and development, 2018, 55(9): 1871-1888
[13] 王晓华, 杨新艳, 焦李成. 基于多尺度几何分析的复杂网络压缩策略[J]. 电子与信息学报, 2009, 31(4): 968-972
WANG Xiaohua, YANG Xinyan, JIAO Licheng. Compression of complex networks based on multiscale geometric analysis[J]. Journal of electronics & information technology, 2009, 31(4): 968-972
[14] YU Jie, TIAN Shen. A review of network compression based on deep network pruning[C]//Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology. Dalian, China, 2019: 324-335.
[15] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer Science, 2012, 3(4): 212?223.
[16] BALDI P, SADOWSKI P. The dropout learning algorithm[J]. Artificial intelligence, 2014, 210: 78-122.
[17] 周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6): 1229-1251
ZHOU Feiyan, JIN Linpeng, DONG Jun. Review of convolutional neural network[J]. Chinese journal of computers, 2017, 40(6): 1229-1251
[18] 李彦冬, 郝宗波, 雷航. 卷积神经网络研究综述[J]. 计算机应用, 2016, 36(9): 2508-2515, 2565
LI Yandong, HAO Zongbo, LEI Hang. Survey of convolutional neural network[J]. Journal of computer applications, 2016, 36(9): 2508-2515, 2565
[19] 陈先昌. 基于卷积神经网络的深度学习算法与应用研究[D]. 杭州: 浙江工商大学, 2014.
CHEN Xianchang. Research on algorithm and application of deep learning based on convolutional neural network[D]. Hangzhou: Zhejiang Gongshang University, 2014.
[20] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA, 2014: 580-587.
[21] 刘亦芃. 一种关于深度学习网络结构的改进策略[D]. 长春: 吉林大学, 2019.
LIU Yipeng. A strategy for improving the structure of deep learning network[D]. Changchun: Jilin University, 2019.
[22] 杨国亮, 许楠, 李放, 等. 关于非线性激活函数的深度学习分类方法研究[J]. 江西理工大学学报, 2018, 39(3): 76-83
YANG Guoliang, XU Nan, LI Fang, et al. Research on deep learning classification for nonlinear activation function[J]. Journal of Jiangxi University of Science and Technology, 2018, 39(3): 76-83
[23] 张永雄, 王亮明, 李东. 基于多示例深度学习与损失函数优化的交通标志识别算法[J]. 现代电子技术, 2018, 41(15): 133-136, 140
ZHANG Yongxiong, WANG Liangming, LI Dong. Traffic sign recognition algorithm based on multi-instance deep learning and loss function optimization[J]. Modern electronics technique, 2018, 41(15): 133-136, 140
[24] WAN Li, ZEILER M, ZHANG Sixin, et al. Regularization of neural networks using dropconnect[C]//Proceedings of the 30th International Conference on Machine Learning. Atlanta, GA, USA, 2013: 1058-1066.
[25] 徐玉华, 曾明. 泊松分布性质及应用研究[J]. 长江大学学报(自科版), 2006, 04: 132-133
XU Yuhua, ZENG Ming. Poisson distribution properties and application research[J]. Journal of Yangtze University (Natural Science Edition), 2006, 04: 132-133
- Similar References:
Memo
-
Last Update:
2020-12-25