An Improved Deep Belief Network Prediction Model Based on Knowledge Transfer

被引:4
|
作者
Zhang, Yue [1 ]
Liu, Fangai [1 ]
机构
[1] Shandong Normal Univ, Sch Informat Sci & Engn, Jinan 250358, Peoples R China
来源
FUTURE INTERNET | 2020年 / 12卷 / 11期
基金
中国国家自然科学基金;
关键词
deep belief network; knowledge transfer; partial least squares regression; prediction; PLSR;
D O I
10.3390/fi12110188
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A deep belief network (DBN) is a powerful generative model based on unlabeled data. However, it is difficult to quickly determine the best network structure and gradient dispersion in traditional DBN. This paper proposes an improved deep belief network (IDBN): first, the basic DBN structure is pre-trained and the learned weight parameters are fixed; secondly, the learned weight parameters are transferred to the new neuron and hidden layer through the method of knowledge transfer, thereby constructing the optimal network width and depth of DBN; finally, the top-down layer-by-layer partial least squares regression method is used to fine-tune the weight parameters obtained by the pre-training, which avoids the traditional fine-tuning problem based on the back-propagation algorithm. In order to verify the prediction performance of the model, this paper conducts benchmark experiments on the Movielens-20M (ML-20M) and Last.fm-1k (LFM-1k) public data sets. Compared with other traditional algorithms, IDBN is better than other fixed models in terms of prediction performance and training time. The proposed IDBN model has higher prediction accuracy and convergence speed.
引用
收藏
页码:1 / 18
页数:18
相关论文
共 50 条
  • [1] Knowledge Transfer-Based Sparse Deep Belief Network
    Yu, Jianbo
    Liu, Guoliang
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (12) : 7572 - 7583
  • [2] Diabetes prediction model based on deep belief network
    Lang, Li-Ying
    Gao, Zheng
    Wang, Xue-Guang
    Zhao, Hui
    Zhang, Yan-Ping
    Sun, Sheng-Juan
    Zhang, Yong-Jian
    Austria, Ramir S.
    [J]. JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING, 2021, 21 (04) : 817 - 828
  • [3] A Security Situation Prediction Method Based on Improved Deep Belief Network
    Li, Yufa
    Zhou, Yuguang
    Hu, Kewei
    Sun, Ning
    Ke, Kai
    [J]. PROCEEDINGS OF 2020 IEEE 2ND INTERNATIONAL CONFERENCE ON CIVIL AVIATION SAFETY AND INFORMATION TECHNOLOGY (ICCASIT), 2020, : 594 - 598
  • [4] Machining Roughness Prediction Based on Knowledge-based Deep Belief Network
    Liu, Guoliang
    Yu, Jianbo
    [J]. Jixie Gongcheng Xuebao/Journal of Mechanical Engineering, 2019, 55 (20): : 94 - 106
  • [5] A Deep Belief Network Based Model for Urban Haze Prediction
    Lu, Huimin
    Song, Jingjing
    Di, Tianyi
    Moradi Kurdestany, Jamshid
    Wang, Hongzhi
    [J]. TEHNICKI VJESNIK-TECHNICAL GAZETTE, 2018, 25 (02): : 519 - 527
  • [6] Lateral and Longitudinal Driving Behavior Prediction Based on Improved Deep Belief Network
    Yang, Lei
    Zhao, Chunqing
    Lu, Chao
    Wei, Lianzhen
    Gong, Jianwei
    [J]. SENSORS, 2021, 21 (24)
  • [7] Wafer yield prediction method based on improved continuous deep belief network
    Xu, Hongwei
    Zhang, Jie
    Lyu, Youlong
    Zheng, Peng
    [J]. Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS, 2020, 26 (09): : 2388 - 2395
  • [8] Image recognition based on improved convolutional deep belief network model
    Wang Hongmei
    Liu Pengzhong
    [J]. Multimedia Tools and Applications, 2021, 80 : 2031 - 2045
  • [9] Image recognition based on improved convolutional deep belief network model
    Wang, Hongmei
    Liu, Pengzhong
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (02) : 2031 - 2045
  • [10] Quality Prediction of Fused Deposition Molding Parts Based on Improved Deep Belief Network
    Dong, Hai
    Gao, Xiuxiu
    Wei, Mingqi
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2021, 2021