改进了GWO及其在Elman神经网络参数优化中的应用
Wei Liu1,2, Jiayang Sun3,1,2, Guangwei Liu4
1Institute of Mathematics and Systems Science, Liaoning Technical University, Fuxin, China.
本研究介绍了一种改进的灰狼优化器 (SGWO),用于神经网络优化. SGWO增强了Elman网络结构和复杂问题的预测准确性.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 计算优化计算优化
背景情况:
- 传统的神经网络由于梯度下降限制而难以进行复杂的优化.
- 开发先进的优化算法对于提高神经网络性能至关重要.
研究的目的:
- 为增强神经网络结构优化提供改进的灰狼优化器 (SGWO).
- 通过将SGWO应用于Elman网络,引入一种新的预测方法SGWO-Elman.
- 通过数学分析SGWO收,并通过实验验证其优化和预测能力.
主要方法:
- 增强的灰狼优化器 (SGWO) 具有圆形人口初始化,信息交互和自适应位置更新.
- 应用SGWO来优化Elman神经网络的结构.
- 使用马尔科夫链理论对SGWO进行数学收分析.
- 进行比较实验来评估SGWO的优化和SGWO-Elman的预测性能.
主要成果:
- SGWO证明了全球收概率为1,作为有限的同质马尔科夫链而起作用.
- 与标准方法相比,SGWO在复杂的多维函数上表现出优异的优化性能.
- SGWO有效优化了Elman网络结构,从而在SGWO-Elman模型中实现了准确的预测性能.
结论:
- 提出的SGWO算法为复杂的问题提供了强大的优化能力.
- SGWO-Elman模型提供了准确的预测,优于Elman网络优化传统方法.
更多相关视频
03:31Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
13:54A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM
Published on: August 18, 2023
相关概念视频
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
On...
Improving Translational Accuracy
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
Reducing Line Loss
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
Neural Regulation
