基于单输出切比雪夫多项式神经网络的海洋矿物分类

Journal of South China University of Technology(Natural Science Edition)(2020)

Cited 0|Views1
No score
Abstract
针对海洋矿物分类问题,提出了改进后的单输出切比雪夫多项式神经网络(single-output Chebyshev-polynomial neural network with general solution,SOCPNN-G).该模型利用伪逆的通解来求参数,扩大解空间,能获得泛化性能更加优良的权重.在该模型中,子集方法用于确定神经元的初始数量和获得交叉验证的最佳重数.最后将改进的SOCPNN-G模型用于海洋矿物数据集中进行实验,结果表明,该模型训练准确率和测试准确率分别达到90.96%和83.33%,且对计算性能要求较低.这些优越性表明该模型在海洋矿物的实际应用中具有很好的前景.
More
Translated text
Key words
marine mineral,classification,single-output Chebyshev-polynomial neural network with generalsolution ( SOCPNN-G),weights,accuracy
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined