[1]魏传佳.逆传输类神经网络中非对称数据优化算法研究[J].信息化理论与实践,2021,(01):140-147.
点击复制

逆传输类神经网络中非对称数据优化算法研究()
分享到：

《信息化理论与实践》[ISSN:2520-5862/CN:]

卷:
期数:
2021年01
页码:
140-147
栏目:
出版日期:
2021-12-31

文章信息/Info

Title:
The Optimization Algorithm Research for Asymmetrical Data of Reverse Transmission Neural NetworkChuan-jia WEI1
作者:
魏传佳
泉州轻工职业学院 智能工学院?
Author(s):
School of Intelligent Engineering, Quanzhou Technology CollegeQuanzhou 362200
关键词:
神经网络 非对称数据 逆向传输 算法有效性
Keywords:
Neural network;  Asymmetric data;  Reverse transmission;  the effectiveness of the algorithm
摘要:
　[目的] 本算法在不影响算法复杂度的情况下，提高了对非对称数据运算的精确性与有效性。[方法] 提出一种修改权重的逆传输类神经网络算法，通过修改自学习效率，对占有较少类的数据分配不通权重来解决非对称平衡问题。[结果] 仿真结果表明，与其他五种分类算法对比，该算法切实解决数据分类的问题。 [局限] 处理海量数据时候，时间冗余度会比较大，如何处理此问题，将在以后的研究中改进。[结论] 解决了逆向传输类神经网络处理非对称数据时效率低下的问题，效果显著
Abstract:
Objective] This algorithm improves the accuracy and effectiveness of operations on asymmetric data without affecting the complexity of the algorithm.[Methods] An inverse transport neural network algorithm with modified weights is proposed, which solves the asymmetric balance problem by modifying the self-learning efficiency and assigning different weights to the data with fewer classes.[Results] The simulation results show that, compared with the other five classification algorithms, this algorithm can effectively solve the problem of data classification.[Limitations] When dealing with massive data, the time redundancy will be relatively large. How to deal with this problem will be improved in future research.[Conclusion] The problem of low efficiency in processing asymmetric data with reverse transmission neural network is solved, and the effect is remarkable

参考文献/References:

[1] LabovitzC, Iekel-JohnsonS, McPherson D, et.al. Internetinter-domaintraffic[C].ACM SIGCOMM Conference.2019
[2]豆育升，崔晟圆，唐 红，李鸿健。(An Energy- efficient Virtual Machine Placement Algorithm in Cloud Data Center)云数据中心高能效的虚拟机放置算法。小型微型计算机系统[J]，2014,35（11）:2543-2547。
[3]Falkenauer E, Delchambre A. A genetic algorithm for bin packing and line balancing[C]. Proceedings of IEEE International Conference on Robotics and Automation.2018.
[4] Gao Y,Guan H,Qi Z, et al. A multi-objective ant colony system algorithm for virtual machine placement in cloud computing[J].Journal of Computer and System Sciences, 2019,79(8):1230-1242.
[5] Nishant K，Sharma P，Krishna V，ct al. Load balancing of nodes in cloud using ant colony optimization[C].International Conference on Computer Modeling and Simulation. :IEEE,201:3-8.
[6] E.H.L.Aarts , P.J.M.Van Laarhoken, a general approach to combinatorial optimization problems[J]. Philips J Res,2017,40(4)193-226.
[7] Gandlii A,Harclio-Balter M，Das R, et al. Optimal power allocation in sever farms[C]. Measurement and Modeling of Computer Systems, ACM，New York, NY，USA , 209:157-168.
[8] Chen G,He W,Liu ,J, et al.Energy-aware server provisioning and load dispatching for connection-intensive Internet services[C].Proceedings of Symposium on Networked Systems Design and Implementation,2018,8:337-350.
[9] Toe, Satori, Touching Performance evaluation of a green scheduling algorithm for energy savings in cloud computing[C]. 2019 IEEE?International?Symposium?on Parallel, 9:30-50.

更新日期/Last Update: 2022-12-20