| 摘要: |
| 文章用一种免疫进化规划来设计多层前馈神经网络.该免疫进化规划在保留传统进化规划的随机全局搜索能力的基础上,引进生物免疫中抗体通过浓度相互作用的机制和多样性保持机制.免疫进化规划的全局收敛性更优,并且具有很强的自适应环境的能力.实验结果验证了免疫进化规划在设计神经网络时的高效能. |
| 关键词: 进化规划,未成熟收敛,免疫,浓度,多样性保持. |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国家自然科学基金和安徽省“九五”重点攻关项目资金资助. |
|
| Design Multilayer Feed-forward Networks Based on Immune Evolutionary Programming |
|
CAO Xian-bin,LIU Ke-sheng,WANG Xu-fa
|
| Abstract: |
| The authors use an immune evolutionary programming to design multilayer feed-forward networks in this paper. The immune evolutionary programming retains the ability of stochastic global searching of traditional evolutionary programming, and draws into the interaction mechanism based on density and the diversity maintaining mechanism which exists in living beings' immune procedure. The immune evolutionary programming has better global convergence and very strong self-adaptive ability with enviornment. The experimental results prove the high efficiency of the immune evolutionary programming in designing neural networks. |
| Key words: Evolutionary programming, premature convergence, immune, density, diversity maintain. |
