Exploiting the Relationship between Pruning Ratio and Compression Effect for Neural Network Model Based on TensorFlow

Pruning is a method of compressing the size of a neural network model, which affects the accuracy and computing time when the model makes a prediction. In this paper, the hypothesis that the pruning proportion is positively correlated with the compression scale of the model but not with the prediction accuracy and calculation time is put forward. For testing the hypothesis, a group of experiments are designed, and MNIST is used as the data set to train a neural network model based on TensorFlow. Based on this model, pruning experiments are carried out to investigate the relationship between pruning proportion and compression effect. For comparison, six different pruning proportions are set, and the experimental results confirm the above hypothesis.

[1]  Xuyun Zhang,et al.  A computation offloading method over big data for IoT-enabled cloud-edge computing , 2019, Future Gener. Comput. Syst..

[2]  Wonyong Sung,et al.  Structured Pruning of Deep Convolutional Neural Networks , 2015, ACM J. Emerg. Technol. Comput. Syst..

[3]  Xuyun Zhang,et al.  A QoS-aware virtual machine scheduling method for energy conservation in cloud-based cyber-physical systems , 2019, World Wide Web.

[4]  Chin-Feng Lai,et al.  An energy-efficient geographic routing protocol design in vehicular ad-hoc network , 2012, Computing.

[5]  Xuyun Zhang,et al.  An edge computing-enabled computation offloading method with privacy preservation for internet of connected vehicles , 2019, Future Gener. Comput. Syst..

[6]  Jiujun Cheng,et al.  TRec: an efficient recommendation system for hunting passengers with deep neural networks , 2018, Neural Computing and Applications.

[7]  Daqiang Zhang,et al.  Query Representation with Global Consistency on User Click Graph , 2013, ArXiv.

[8]  Yu Wang,et al.  Software-Hardware Codesign for Efficient Neural Network Acceleration , 2017, IEEE Micro.

[9]  Xinping Yan,et al.  An advanced fuzzy Bayesian-based FMEA approach for assessing maritime supply chain risks , 2019, Transportation Research Part E: Logistics and Transportation Review.

[10]  Xinping Yan,et al.  An Evidential Reasoning‐Based CREAM to Human Reliability Analysis in Maritime Accident Process , 2017, Risk analysis : an official publication of the Society for Risk Analysis.

[11]  C. Guedes Soares,et al.  Incorporating evidential reasoning and TOPSIS into group decision-making under uncertainty for handling ship without command , 2018, Ocean Engineering.

[12]  Kening Zhu,et al.  PaperIO: A 3D Interface towards the Internet of Embedded Paper-Craft , 2014, IEICE Trans. Inf. Syst..

[13]  Tao Huang,et al.  An energy-aware computation offloading method for smart edge computing in wireless metropolitan area networks , 2019, J. Netw. Comput. Appl..

[14]  Zibin Zheng,et al.  Covering-Based Web Service Quality Prediction via Neighborhood-Aware Matrix Factorization , 2019, IEEE Transactions on Services Computing.

[15]  E. Zio,et al.  A resilience perspective on water transport systems: The case of Eastern Star , 2019, International Journal of Disaster Risk Reduction.

[16]  Xuyun Zhang,et al.  Spatial-temporal data-driven service recommendation with privacy-preservation , 2020, Inf. Sci..

[17]  Mehul Motani,et al.  An Optimal Cross-Layer Framework for Cognitive Radio Network Under Interference Temperature Model , 2016, IEEE Systems Journal.

[18]  Xuyun Zhang,et al.  Finding All You Need: Web APIs Recommendation in Web of Things Through Keywords Search , 2019, IEEE Transactions on Computational Social Systems.

[19]  Qiang He,et al.  Efficient Query of Quality Correlation for Service Composition , 2018, IEEE Transactions on Services Computing.

[20]  Chaozhong Wu,et al.  Incorporating CREAM and MCS into fault tree analysis of LNG carrier spill accidents , 2017 .

[21]  Jiann-Liang Chen,et al.  RFID-based mobility for seamless personal communication system in cloud computing , 2015, Telecommun. Syst..

[22]  Haibin Zhu,et al.  Location-Aware Deep Collaborative Filtering for Service Recommendation , 2021, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[23]  Rongbo Zhu,et al.  Enhanced MAC protocol to support multimedia traffic in cognitive wireless mesh networks , 2011, Multimedia Tools and Applications.

[24]  Tapani Ristaniemi,et al.  Guest Editorial , 2011 .