改进鲸鱼优化算法及其浅层神经网络结构搜索方法研究
作者:
作者单位:

辽宁工程技术大学

作者简介:

通讯作者:

中图分类号:

TP18

基金项目:

基于时空序列反演的露天矿物料流量流向动态优化研究(51974144);露天煤矿顺倾软岩边坡失稳时空演化机制与稳定性计算方法(51874160);辽宁 工程技术大学学科创新团队资助项目(LNTU20TD-01, LNTU20TD-07)


Research on Shallow Neural Architecture Search Method Based on Improved Whale Optimization Algorithm
Author:
Affiliation:

1.辽宁工程技术大学;2.Liaoning Technical University

Fund Project:

Study on dynamic optimization of material flow direction of open-pit mine based on spatiotemporal sequence inversion(51974144);Spatial-temporal evolution mechanism and stability calculation method of downdip soft rock slope in opencast coal mine(51874160);Project supported by discipline innovation team of Liaoning Technical University(LNTU20TD-01, LNTU20TD-07)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为设计出简便高效的方法搜索最优神经网络结构, 本文提出了一种改进鲸鱼优化算法的浅层神经网络搜索方法. 该方法首先通过模拟鲸鱼狩猎的个体偏好行为和鲸鱼群位置移动的非线性权值更新机制对传统鲸鱼优化算法进行改进; 然后将改进鲸鱼优化算法作为浅层BP神经网络结构搜索策略, 构建了基于浅层BP神经网络的最优网络结构的权值阈值搜索优化方法. 数值实验结果表明: 改进的鲸鱼优化算法不仅在求解不同维复杂函数上具有良好的寻优性能, 而且通过改进鲸鱼优化算法搜索得到的最优浅层BP神经网络结构在回归任务中具有更好的预测精度和泛化性能.

    Abstract:

    In order to design a simple and efficient method to search for the optimal neural network architecture, we propose an improved whale optimization algorithm and its shallow neural architecture search"s weights and thresholds optimization. This method first improves the traditional whale optimization algorithm by simulating the individual preference behavior of whale hunting and the nonlinear weight update mechanism of whale group position movement; then, the improved whale optimization algorithm is used as a shallow BP neural network architecture search strategy, and a architecture based on the optimization method of weight threshold search for the optimal network architecture of shallow BP neural network. The numerical experimental results show that the improved whale optimization algorithm not only has good optimization performance in solving complex functions with different dimensions, but also the optimal shallow BP neural network architecture searched by the improved whale optimization algorithm has better prediction accuracy and generalization performance in regression tasks.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-10-07
  • 最后修改日期:2021-12-30
  • 录用日期:2021-12-30
  • 在线发布日期: 2022-02-01
  • 出版日期: